shiply

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds context beyond annotations: 'detect its DNS provider', 'one-click connect', and guidance to use add_subdomain next. Annotations indicate idempotent and open world, which are consistent with registration behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with action and returns, no unnecessary words. Efficient and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with output schema and rich annotations, the description fully covers what the tool does, what it returns, and the next step. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline 3 is appropriate. The description repeats schema info ('registrable domain you own') but doesn't add significant new semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Register', the resource 'custom domain', and specifies it detects DNS provider and returns provider/one-click connect availability. It distinguishes from siblings like add_subdomain by noting the subsequent step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use (registering a user-owned domain) and mentions the next step (add_subdomain). It provides context but doesn't explicitly state when not to use or list alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate idempotent and open-world. The description adds valuable behavioral details: returns CNAME, certificate issues automatically after DNS resolves, and suggests polling with check_domain. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences that are front-loaded with purpose, no superfluous words, and clear structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given low complexity and rich schema/annotations, the description covers the tool's operation, return value, and next steps. It could mention prerequisites (e.g., domain ownership) but that is already implied.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are well-described. The description adds only minor context (hostname example, slug reference), so it meets the baseline but does not exceed it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool serves a site on a user-owned domain, with a specific verb and resource. It distinguishes from siblings like add_custom_domain by focusing on serving a site and returning the CNAME.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use (to serve a site on a domain) and what to do after (poll with check_domain). It does not explicitly list alternatives or when not to use, but it is adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations declare openWorldHint=true and idempotentHint=true, and the description adds meaningful behavioral context: the tool returns DNS records (SPF, DKIM, MX) and requires subsequent verification. It does not contradict any annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with three well-structured sentences. The first sentence immediately states the primary purpose, and subsequent sentences provide necessary details without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple single-parameter tool with an output schema (implied), the description covers all essential aspects: purpose, required resource, return type, follow-up action, and a constraint. It is fully adequate for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for its only parameter 'domain', with an example ('e.g. mail.yourbrand.com'). The description does not add additional semantics beyond the schema, so a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Register a domain'), resource ('the user owns'), and purpose ('for outbound demand-test sends'). It also specifies that DNS records will be returned and the next step (call verify_sending_domain). This effectively distinguishes it from sibling tools like add_custom_domain or add_domain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context: it registers a domain for sending and requires DNS propagation and verification. It also explicitly states a constraint ('Cannot be a shiply.now subdomain'). However, it does not mention when not to use this tool or direct alternatives, so a slight deduction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide openWorldHint and idempotentHint, indicating safe side effects and idempotency. The description adds behavioral details: auto-registers parent domain, returns CNAME record, and automatic certificate issuance after DNS resolves. This provides useful context beyond annotations, though it could mention if there are any destructive steps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, covering the main function, apex handling, follow-up action, and return value. It is efficiently written with zero wasted words, front-loaded with the core purpose, and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (3 required params, no nested objects), the description is complete. It explains the return value (CNAME record) and the subsequent step (poll with check_domain). The presence of an output schema (not shown) further reduces the need to describe return format. No gaps identified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions for each parameter. The description reiterates the schema's definitions (e.g., 'owned site slug', 'registrable parent domain') but does not add new meaning or format details. Baseline 3 is appropriate as schema already documents the parameters effectively.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Serve an owned site at <subdomain>.<domain>') and specifies the resource (subdomain on a domain). It distinguishes from siblings like add_domain by focusing on subdomain mapping and includes special handling for apex. The verb 'point' and resource 'subdomain' are specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage context: use when you want to serve a site at a subdomain. It mentions apex requirements and advises polling with check_domain. However, it does not explicitly state when not to use this tool or list alternatives (e.g., add_custom_domain), so it's slightly lacking in exclusion guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate idempotentHint=true, and the description adds behavioral context by stating that suppressed addresses are skipped across every test for future confirmations and broadcasts. This goes beyond the annotation without contradicting it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences convey the purpose, effect, and parameter usage with no wasted words. The description is front-loaded with the action and immediately informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema (not shown) and good annotations, the description covers the tool's effect adequately. It mentions cross-test impact, but could briefly mention return value format; still, it is largely complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description reinforces the schema examples but does not add new parameter details beyond what is already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool adds an address or domain to the suppression list, with clear distinction from sibling tools like remove_suppression. The effect on future confirmations and broadcasts is specified, making the purpose unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use kind='email' vs kind='domain', covering the two main use cases. It does not explicitly state when not to use the tool, but the context is sufficient for an AI agent to decide appropriately.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the idempotentHint annotation, the description explains the specific behavioral effect (status change, hidden from dashboard) and the optional reason display. It does not contradict annotations and provides useful context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, zero waste: action stated first, then effect, then restoration option. Front-loaded with the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 params, output schema exists, idempotentHint) and sibling context, the description covers the key points: what it does, behavioral effect, and how to revert. It does not explain the output format, but that is handled by the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description merely reiterates the parameter purpose ('optional reason is shown on the project page') without adding new meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Move') and resource ('project'), explicitly stating the status change to 'archived' and the effect of hiding from dashboard. It distinguishes from sibling tools like 'archive_thread' and mentions the counterpart 'restore_project'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates when to use the tool (to hide a project from default list without deletion) and provides an alternative for reversal ('Restore later with restore_project'), though it lacks explicit exclusions or when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds key behavioral details beyond the idempotentHint annotation: it is a 'soft-archive' (mutates a field), it hides the thread from default view but makes it accessible via a filter, and it is reversible. This fully informs the agent of the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, consisting of two short sentences that convey all necessary information without any redundant or extraneous text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple nature of the tool (one parameter, straightforward effect), the description completely and adequately explains the tool's purpose, behavior, and context. No additional information is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the parameter 'threadId' is described in the schema as 'thread id from list_inbox to archive'. The description adds no additional semantic information beyond what the schema provides, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'soft-archive' and the resource 'thread', specifying the effect of setting 'archivedAt'. It distinguishes itself from related tools like 'unarchive_thread' and 'list_inbox'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use the tool (to hide from default inbox) and how to reverse it with 'unarchive_thread'. It also notes that the thread can be surfaced again with a filter. However, it does not explicitly state when not to use it or provide alternatives beyond the reverse operation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate idempotentHint=true. The description adds behavioral context beyond annotations by explaining that the binding takes effect on the next deploy, implying a non-immediate effect. This provides useful transparency without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loads the action, and contains no unnecessary words. Every sentence adds value, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple attachment tool with two required parameters, high schema coverage, annotations, and an output schema, the description is fully complete. It explains the action, timing, and prerequisite without needing to elaborate on return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers 100% of parameters with clear descriptions (database id from list_databases, owned site slug). The description adds context about the binding name set at creation, but this does not significantly enhance understanding of the parameters themselves. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('bind an existing database to one owned site's Worker env') and identifies the specific resources (database, site). It distinguishes from sibling tools like create_database and delete_database by focusing on binding an existing database rather than creating or deleting.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context by stating that the binding takes effect on the next deploy and mentions the prerequisite that the binding name was set at create_database time. However, it does not explicitly list alternatives or when not to use this tool, though the context is sufficiently specific.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds behavioral details beyond annotations: binding type (plain_text), opt-in per site, effect on next function deploy. Consistent with idempotentHint=true. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences with no fluff: core action, security context, and deployment timing. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a simple tool with two params and an output schema. Explains binding type, effect timing, and optional nature. Lacks explanation of 'Worker env' implications but output schema likely covers return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers both parameters with descriptions (name, slug) at 100% coverage. Description reinforces 'saved variable' and 'owned site' but adds minimal new semantics beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool exposes a saved variable to one owned site's Worker environment as a plain_text binding. It specifies the resource (variable) and target (site), and distinguishes from siblings like delete_variable, set_variable, or attach_database.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context: use when you need a variable accessible to a site's Worker, and notes unattached variables are never injected. Does not explicitly name alternatives or exclusions, but gives enough guidance for correct use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description adds significant behavioral context beyond annotations: re-polls cert, probes DNS/TLS/HTTPS, and returns per-subdomain status. No contradiction with read-only and open-world hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler. Front-loaded with main action, then additional context. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given one required parameter, annotation hints, and existence of output schema (not shown), the description covers what it does and what it returns. No gaps for typical usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single parameter with schema providing description and example. The description repeats the parameter purpose but adds no extra semantics beyond the schema; however, the example is helpful. With 100% schema coverage, baseline is 3, so 4 for the example.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it checks if a custom domain's subdomains are live, with specific actions (re-polls Cloudflare cert, probes DNS/TLS/HTTPS). It distinguishes from siblings like check_domain by mentioning it is used after connect_provider/add_subdomain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to poll after connect_provider or add_subdomain to confirm domain is serving. While it doesn't list when not to use or alternatives, the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint; the description adds context that it performs a live probe, which aligns with openWorldHint and provides transparency beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with key action and resource, no redundant words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With full schema coverage, annotations, and an output schema, the description fully explains the tool's behavior and parameter source; no gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%; the description merely restates the schema's parameter description ('connected domain id from list_domains'), adding no new meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies the action ('refresh certificate status + live TLS/HTTPS probe') and the resource ('connected domain'), and distinguishes from siblings by requiring the domain id from list_domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly implies the prerequisite of having a domain id from list_domains, but does not explicitly state when to use this tool over alternatives like check_custom_domain.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (openWorldHint, idempotentHint), the description discloses key behaviors: Cloudflare returns an authorize URL and auto-writes records after authorization; other providers require manual record addition. This adds value without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded purpose, no wasted words. Every sentence is essential: one for the action, one for provider-specific instructions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (two scenarios), one parameter, and the presence of an output schema, the description is complete. It covers the key behavioral difference and guides the agent on handling Cloudflare vs. other providers.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single parameter 'domain'. The description adds minimal extra meaning beyond the schema's 'registered custom domain to connect'—it provides an example but no new semantic detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Start one-click DNS connect') and the resource ('registered custom domain'), with specific verb and resource. It distinguishes between Cloudflare and other providers, setting it apart from sibling tools like add_domain or check_domain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: for Cloudflare hosts, show the authorize URL; for others, add records manually. It does not explicitly state when not to use it, but the context is clear. Sibling tools imply prerequisites like adding a domain first.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses that the tool creates a draft amendment (non-destructive creation) and requires a signed parent contract. The idempotentHint=false annotation is honored; the description adds context about the two-step process and state requirement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no fluff. Front-loaded with core purpose, followed by workflow and constraint. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and full parameter descriptions, the description adequately covers the creation workflow, state prerequisites, and integration with contract_send. No gaps for agent decision-making.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema already covers all parameters (100% coverage), but the description adds workflow context (e.g., 'scope delta required; fee delta and target date optional') and constraint ('negative for descope' reinforces schema). Minor extra value beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Create' and the resource 'amendment to a SIGNED parent contract'. It distinguishes from siblings like contract_draft and contract_send by specifying the workflow and constraints (e.g., cannot amend an amendment).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use (create amendment to signed parent) and when-not (cannot amend an amendment). Also guides next steps ('call contract_send with the returned amendment id to fire it') and clarifies required/optional parameters.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that it auto-fills 8 fields, uses default currency and dev profile, and returns a draft status. This adds behavioral context beyond the idempotentHint annotation. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loads the primary purpose, and then concisely adds workflow context. Every sentence provides value with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the single parameter, annotations, and presence of an output schema, the description fully explains the tool's behavior, return value (contract row with status='draft'), and subsequent steps (edit and send). No gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The sole parameter 'projectId' has a schema description ('Project to draft a contract for') that already clarifies its purpose. The description does not add additional semantics beyond what the schema provides, meeting the baseline for 100% coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Draft a contract') and the resource ('a brief_ready project'). It explains the auto-fill behavior and return value, and contrasts with sibling tools like contract_amend and contract_send, providing clear differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description outlines the workflow: draft from brief_ready project, then edit via PATCH API (noting no MCP edit tool yet), then call contract_send. This provides context for when to use and what to do next, though it does not explicitly state when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only. The description adds detail about the PDF content (contract, signature, amendments) and the return format, as well as the specific error case. This goes beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, no wasted words. Each sentence adds value: purpose/output format, content details, error condition. Front-loaded with main action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description sufficiently covers behavior, return structure, and a key error. Minor omission of other potential errors (e.g., invalid ID), but adequate for a simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the description does not add significant new semantics beyond the schema's description of contractId as 'signed contract id'. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves a signed contract PDF as base64, specifying the resource (signed contract PDF) and verb (get). It distinguishes from sibling tools like contract_status or contract_draft by focusing on PDF download.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for signed contracts via the error condition, but does not explicitly state when to use over alternatives like contract_status. No direct comparison with siblings is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses validation, content_hash computation, state change to contract_sent, and email firing. Also clarifies amendment behavior. No annotation contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with purpose. Every sentence provides essential information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given one parameter, output schema, and annotations, the description covers validation, state changes, email, and amendment handling comprehensively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Parameter contractId is well described in schema. Description adds context about field validation, enhancing understanding beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Send a draft contract to the customer.' Differentiates from siblings by noting amendment drafts do not move project state, distinguishing from contract_amend and contract_draft.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides context on when to use: validates all 8 fields are non-empty, and works for both regular and amendment drafts. Lacks explicit when-not alternatives, but implicit guidance is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, and the description reinforces a read-only behavior ('Read the current state...'). It further discloses the precise shape of the return value ('Returns { contract, amendments }'), adding value beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loaded with purpose and key fields, followed by a usage hint and return structure. Every sentence serves a clear function; no extraneous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a single-parameter read-only tool with an existing output schema (not shown but referenced), the description is complete. It tells the agent exactly what data is returned and when to use it, leaving no ambiguity for a simple read operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is only one parameter with 100% schema coverage. The description restates the parameter's function ('contract id to read state for'), which aligns with the schema's description. No additional semantic nuance is added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Read') and resource ('current state of a contract') and enumerates key fields (status, timestamps, signer info, content_hash, amendments). It distinguishes itself from sibling tools like contract_amend, contract_draft, contract_send.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states a use case ('Use this to check whether a customer has signed yet'), providing clear context for when to apply the tool. It does not formally outline when not to use it, but the purpose is unambiguous among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide idempotentHint=true. The description adds value by disclosing provider plans (free D1, developer Neon), default behavior, and the attachment integration. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the main action and provider options, then adding the optional attachment detail. Every word is necessary and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 4 parameters, 1 required, and an output schema, the description covers the core workflow. It could mention the binding parameter's role more explicitly, but overall it is sufficient for an agent to select and use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so each parameter is documented. The description adds integration context (siteSlug for immediate attachment, provider selection via --postgres) beyond the schema. This enriches understanding without repeating schema details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provisions a SQL database with specific providers (D1 or Neon) and optionally attaches it to a Worker environment. It differentiates from sibling tools like attach_database by indicating that attachment can be done in the same call or later.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear when-to-use guidance: it shows the default provider (D1) and alternative (Neon with --postgres), and explains how to attach immediately via siteSlug or later via attach_database. It does not explicitly state when not to use it, but the optionality is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the creation operation and mentions plan limitations, adding context beyond the idempotentHint annotation. However, it does not detail the behavioral impact (e.g., immediate availability, response structure) or error scenarios.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two short sentences that convey the essential information without any filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and the simplicity of the tool, the description is fairly complete. It covers the creation action, resource type, plan restriction, and optional client association. Missing details like error handling are minor for this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already describes both parameters with 100% coverage. The description adds minor value by mentioning the client parameter's purpose ('file it under a client'), but does not provide new information beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action 'Create a private cloud Drive' and specifies the resource type and a constraint ('plan-limited'). It distinguishes from sibling drive tools like list_drives and drive_delete_file by focusing on creation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides guidance on the optional client parameter ('Pass client to file it under a client'), which helps the agent understand when to use that parameter. However, it does not explicitly state when to use this tool versus alternatives or list exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds behavioral context beyond annotations (only idempotentHint: false) by stating the action is an upsert and listing acceptance criteria (e.g., price range, termsMode constraints). However, it does not disclose side effects like what happens on success/failure, whether it overwrites existing data, or any irreversible consequences.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the main action, followed by a prerequisite and parameter details. Every sentence is essential, and there is no fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema (not shown), the description does not need to explain return values. It covers prerequisites, constraints, and parameter details. However, it could be more complete by explaining the upsert behavior (e.g., how it identifies existing listings) and potential side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds value by clarifying that termsMode='custom' requires termsCustom ≥50 chars (not in schema) and provides example for jurisdiction. This enriches the parameter meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action: 'Publish (or upsert) a marketplace listing for an owned site.' It uses a specific verb-resource combination and distinguishes from siblings like update_listing and delete_listing through the 'upsert' hint.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies a prerequisite: 'Requires Stripe Connect set up (status='ready' — see get_connect_status).' This provides clear context for when to use the tool. However, it lacks explicit guidance on when not to use it or how it differs from update_listing, such as whether to use create_listing for new listings and update_listing for existing ones.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses side effects (email sending) and return values (project row, intakeUrl), though no explicit mention of idempotency or failure modes. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with front-loaded main action, no redundant information, every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers main behavior and return values for a creation tool with an output schema; could mention required parameter 'label' but schema handles that.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds meaningful context beyond schema descriptions by explaining the overall flow and purpose of parameters, such as linking to a site for redesign.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the verb 'spin up' and resource 'customer-intake project', distinguishing it from siblings like list_projects, get_project, archive_project, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides context for when to use optional parameters (customerEmail triggers email, originatedFromSiteId links to site), but lacks explicit exclusion of alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the idempotentHint=false annotation, the description discloses the full workflow: deployment, subscriber segment creation, double-opt-in confirmation for signups, and return of testId and siteUrl. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with two sentences that front-load the primary action and follow with essential details. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and the tool's complexity, the description covers all necessary context: what it does, what it returns, and how to use the results. It is self-contained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description does not add extra semantics to the parameters beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it provisions a demand test, deploys a landing page with a native email-capture form, creates a confirmed-subscriber segment, and returns testId and siteUrl. It is distinct from sibling tools like list_tests and get_test_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the use case (one-call provisioning of a demand test) and suggests sharing the siteUrl and monitoring progress with get_test_status. It does not explicitly mention when not to use or alternatives, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Consistent with readOnlyHint annotation. Adds concrete behavioral details: limit capping (default 1000, max 5000) and the fact that records are returned up to the limit. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the main action and limits. No wasted words; the alternative CLI command is a concise addition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, so return values need not be described. Tool is simple (export records with limit); description covers purpose, limits, and alternatives, making it fully adequate for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, baseline 3. Description restates the limit parameter's default and max but adds no new semantic meaning beyond what the schema already provides. Does not elaborate on slug or collection beyond their names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb (return/export), resource (records from a collection), and purpose (snapshotting into agent context). Distinguishes from siblings like data_query by explicitly noting the CLI alternative for larger sets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (small exports for agent context) and when not to (larger sets → CLI). Also provides default and max limit values, giving clear usage boundaries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds behavioral context by noting the endpoint is a public visitor endpoint and that 'manifest access.insert' determines permission. However, it does not discuss idempotency (annotations already note idempotentHint=false) or error handling. Overall, it provides some value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly concise at two sentences. The first sentence defines the core function, and the second provides context and use cases. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (3 params, nested object, output schema), the description is fairly complete. It covers purpose, endpoint, and use cases. While it omits details like return format, the presence of an output schema mitigates this. Some minor gaps remain (e.g., behavior on duplicate), but overall reasonable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add significant meaning beyond what the schema already provides for parameters (slug, collection, record). It mentions 'record' but without extra detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Insert one record into a collection.' It uses a specific verb ('Insert') and resource ('record'), and includes example use cases ('seed waitlist data, test forms end-to-end'), effectively distinguishing it from sibling tools like data_export_collection and data_query.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage context ('Use to seed waitlist data, test forms end-to-end') and implies when to use this tool (for inserts). It does not explicitly state when not to use it, but the sibling tools cover reads and exports, making the guidelines adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint: true, and the description aligns with a read operation. It adds valuable context: the tool returns current record counts, and an empty list means no manifest exists. It also suggests a CLI command for scaffolding. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: the first directly states the purpose, and the second adds actionable context for an edge case. No unnecessary words; information is front-loaded and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema (not shown), the description adequately covers the tool's behavior: it lists collections with counts and explains empty results. It might be enhanced by noting any ownership constraints or limits, but it is sufficient for a simple read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage with a single 'slug' parameter described as 'owned site slug.' The description does not add further semantic detail beyond what the schema provides, meeting the baseline expectation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'List' and the specific resource 'collections declared in an owned site's .shiply/data.json with current record counts.' It distinguishes itself from siblings like data_insert and data_query by focusing on listing collection metadata. The mention of an empty list hinting at scaffolding further clarifies the tool's purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool (to list collections) and interprets an empty result as a signal to scaffold a manifest. However, it does not explicitly state when not to use it or mention alternative tools for data manipulation, though this is implied by the name and sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true. Description adds behavioral context: returns records newest-first and paginated. Could disclose rate limits or auth needs, but ordering and pagination are valuable additions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no extraneous words. Every sentence provides essential information about pagination, ordering, and constraints. Highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters, annotations, and output schema existence, the description covers pagination mechanism, parameter constraints, and ordering. No major gaps for a paginated read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, baseline 3. Description adds defaults for limit (50) and source for cursor (previous nextCursor), plus clarifies slug and collection context beyond schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'page records', the resource 'owned site's collection', and ordering 'newest-first'. It distinguishes from sibling tools like data_insert and data_list_collections by specifying pagination and ordering.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides concrete usage constraints: limit ≤200 (default 50), cursor from previous nextCursor. However, it does not explicitly compare to alternatives like data_export_collection for full exports.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description adds 'PERMANENTLY' and 'Irreversible' beyond the destructiveHint annotation, providing clarity on the irreversible nature. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the critical warning. No extraneous information. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter destructive tool with an output schema and annotation, the description sufficiently covers the action, its permanence, and usage caution. Complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and already describes the 'id' parameter as 'database id (from list_databases)'. Description does not add further meaning beyond that.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'PERMANENTLY delete a database and all its data' with specific verb 'delete' and resource 'database'. Distinguishes from siblings like delete_listing, delete_site, etc., by specifying database.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly warns that the action is irreversible and requires user confirmation, guiding the agent on when to use. Does not explicitly mention alternatives, but no alternative exists for deleting a database.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the destructiveHint annotation, description reveals the soft-delete nature (keeps row, enables re-listing), the status change to draft, and the restriction on sold listings, adding valuable behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences front-load the purpose, include key details, and contain no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a single param fully described, annotations providing destructiveness context, and the description covering behavior, usage, and constraints, the tool is fully specified for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only parameter siteSlug is well-described in schema (100% coverage). Description does not add further meaning to the parameter, which is acceptable given the baseline of 3 for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'take a listing off the public marketplace' and the resource 'listing', distinguishes from hard delete, and notes sold listings can't be modified, differentiating it from siblings like update_listing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'Use to stop accepting offers without losing pricing history' and notes constraints (sold listings can't be modified), providing clear guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds behavioral context beyond the destructiveHint annotation by emphasizing permanence, irreversibility, and inclusion of all stored files. It also recommends user confirmation, which annotations alone do not provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that immediately conveys the critical information (permanence, resource, scope) with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple delete tool with one parameter and an output schema, the description fully explains the irreversible consequences and what is deleted (site and files), meeting completeness needs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The parameter 'slug' is fully described in the schema ('site slug to delete'); the description adds no extra meaning beyond confirming it identifies the site. With 100% schema coverage, this is adequate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'PERMANENTLY delete a site and all stored files,' using specific verb and resource, and distinguishes from sibling delete tools (e.g., delete_database) by specifying 'site' and 'all stored files'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description advises 'confirm with the user first,' implying caution and appropriate context for irreversible actions. It does not explicitly compare to alternatives but provides clear guidance on when to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds no behavioral context beyond the existing 'destructiveHint' annotation. It does not disclose what happens upon deletion (e.g., permanent removal, cascading effects) or any permissions required. With the annotation present, the description fails to provide additional useful context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that immediately conveys the purpose. There is no unnecessary content, and the key action is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple destructive tool with one parameter and an output schema, the description covers the essential purpose. However, a note about permanence or confirmation behavior would improve completeness, given the destructive nature.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description mentions 'by name', which matches the schema's required 'name' parameter, but adds no extra semantics such as naming conventions or constraints beyond the schema description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Remove one variable by name.' clearly states the action and resource. It is specific with the verb 'Remove' and the resource 'variable', and it indicates the key parameter 'by name'. However, it does not explicitly distinguish from sibling tools like 'detach_variable' or 'set_variable', which handle related operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No usage guidance is provided. The description does not indicate when to use this tool over alternatives such as 'detach_variable' or 'set_variable', nor does it mention prerequisites or side effects like irreversibility.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that the function runs on every request, supports webhooks and crons, and requires a Developer plan. Annotations only provide idempotentHint; the description adds value but lacks details on conflict behavior (e.g., overwriting existing functions) or any side effects beyond deployment.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise: two sentences plus a usage line, all front-loaded. Every word adds value with no repetition or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, the description covers the main purpose, capabilities, and usage context. It does not mention prerequisites like the site needing to exist (though implied by the required slug). An output schema exists, so return value details are not needed. Overall adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so each parameter is already described. The description adds overarching context (function capabilities) but does not provide additional meaning to individual parameters beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it deploys a Worker function to a site, specifying the target URL pattern and capabilities like webhooks, cron triggers, and bindings. It distinguishes from siblings like publish_site (static sites) and set_cron (managing crons on existing functions).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Use when the user wants webhook receivers, cron jobs, or a backend for their site.' and mentions 'Requires Developer plan.' This provides clear context for when to use, though it does not explicitly mention when not to use or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations note destructiveHint=true; description adds crucial timing detail 'Takes effect on the site's next function deploy' beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no wasted words. Action verb first, then effect timing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with output schema and annotations, description covers the key behavioral aspect (detach and deploy timing). Nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and both parameters are well-described. Description adds no extra meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses specific verb 'stop exposing' and resource 'variable to a site's Worker env', clearly distinguishing from sibling tools like attach_variable and delete_variable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidelines for when to use this tool versus alternatives like delete_variable or set_variable. Usage is implied but not clarified.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation already marks the tool as destructive (destructiveHint: true). The description adds minimal behavioral context beyond that; it does not mention irreversibility or recovery options.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence with no unnecessary words or details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple 2-parameter structure, the description is adequate but could be more complete by noting that the operation is permanent or specifying any required permissions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are described in the schema. The description adds no additional meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Delete') and the resource ('a file from a Drive'). It is distinct from sibling tools like drive_list_files and drive_put_file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool, any prerequisites (e.g., file existence), or alternatives for similar operations. The description only states the action.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description does not contradict the readOnlyHint annotation, but it adds minimal behavioral context beyond the annotation. It does not mention pagination, ordering, or error handling, which are typical for list operations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 13 words, efficiently conveying the core purpose with no extraneous information. Front-loaded and to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and the simple nature of a list operation, the description is mostly complete. It could clarify the 'prefix filter' behavior, but overall it adequately covers the tool's functionality.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the description largely restates the schema's parameter descriptions. No additional parameter semantics are provided, so it meets the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List files'), the resource ('in a Drive'), and specifies the driveId format with an optional prefix filter. This distinguishes it from sibling tools like drive_delete_file or drive_put_file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like list_project_files. The usage is implied by context but not spelled out. A brief statement about when not to use it would improve clarity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare idempotentHint=true, indicating safe repeated calls. The description adds encoding details (utf8/base64) and drive ID format but does not specify whether the tool overwrites existing files or creates new ones. This missing information is relevant for understanding behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the purpose and key constraints. Every word is relevant, with no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that an output schema exists and annotations provide safety context, the description covers core purpose and use cases. However, it omits overwrite behavior, which is a minor gap for a write tool with idempotent hint. Still, it is largely complete for its complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% parameter description coverage, so the schema already explains each parameter. The description reiterates content encoding but adds no meaningful new semantic information beyond what is in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool writes a file into a Drive, specifies the driveId format, and lists use cases like memory, notes, context, and assets. This distinguishes it well from siblings like drive_list_files and drive_delete_file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit use cases (agent memory, notes, context, assets) but does not offer when-not-to-use guidance or name alternative tools for similar tasks. The context is clear but lacks exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only provide idempotentHint=false. Description adds behavioral details: server-side copy, instantly live, and explicit list of copied vs. non-copied attributes. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states core functionality, second lists copied attributes and use case. No redundancy, front-loaded, efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given simple 2-parameter tool with output schema, description covers what, how, and why. Addresses scope (copied vs. non-copied) and typical use case, making it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both parameters described. Description reinforces that slug is the new slug and title is optional defaulting to source, but adds limited new meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb 'duplicate' and resource 'site' with clear scope: server-side copy under new slug, instantly live. Distinguishes from siblings by listing what is copied (files+title) and what is not (access, domains, data).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('Great for iterating on variants') and implicitly when not (if you need to copy access settings, domains, or data). Could be improved by naming alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, and the description adds behavioral context: what data is included (profile, sites, drives, metadata) and specifically excluded (secrets). This goes beyond the annotation to inform the agent of output content and scope.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first sentence packs the essential information, second sentence is a simple tag. No wasted words, and key details are front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and an output schema, the description adequately covers output contents and exclusion of secrets. Could mention potential size or synchronous nature, but current detail is sufficient for a straightforward export.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters defined in the input schema, so description does not need to add parameter info. Baseline score of 4 applies as there is nothing missing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Return' and clearly defines the resource as a JSON bundle of user account data, listing exact contents. It distinguishes from siblings by focusing on full account export versus individual data retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like data_export_collection or get_account_status. The phrase 'Data portability' implies a use case but does not establish clear conditions or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide idempotentHint. The description uses 'Toggle' which could be misinterpreted as a flip rather than the setter indicated by the input schema (show boolean). It adds the eligibility condition but does not clarify error behavior or side effects beyond what schema suggests.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences cover purpose and constraint with no redundancy. Front-loaded with the action and resource. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, so return values are covered. The description covers purpose, eligibility, and context (gallery URL). Missing details about error conditions or side effects like notifications, but acceptable for a simple boolean-setter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline 3. The description adds context about the gallery and eligibility but does not enhance understanding of the parameters beyond their schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool toggles whether a site appears in the public Explore gallery, specifying the verb (toggle) and resource (site on Explore), with a link and eligibility condition (public-access only). It is easily distinguishable from sibling tools like promote_site or publish_site.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implicitly indicates when to use (when you own a public site and want to show/hide it on Explore) but does not explicitly compare with alternatives or state preconditions like site ownership. It mentions eligibility but lacks when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description details body composition, alias usage, subject default, and optional note, adding significant behavioral context beyond the simple annotations (openWorldHint, idempotentHint). No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences front-load key information without waste. Each sentence serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists and parameters are well-described, the description covers forwarding behavior, body format, alias routing, and defaults completely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 5 parameters have schema descriptions (100% coverage), and the tool description adds rich context like default message selection and subject prefix.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'forward', the resource 'a message from a thread', and specifies default behavior (most recent message). It distinctly separates from siblings like send_email or reply_to_thread.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use (forward to a new recipient, using the thread's alias) but doesn't explicitly contrast with alternative tools like send_email or reply_to_thread.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description details the return values: plan id, name, subscription status, hard limits, and a capability matrix. It also notes that upgrade_url is human-clickable. Annotations already mark it as readOnlyHint=true, and the description adds valuable behavioral context without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single paragraph that front-loads the purpose in the first sentence. It is informative but could be slightly more compact; however, it earns its place with clear, direct statements.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters and the presence of an output schema (implied by the detailed return description), the description is fully complete. It covers what the tool does, when to use it, and what it returns, leaving no gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so the description does not need to explain them. Per the calibration, 0 params yields a baseline of 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get the signed-in account's plan, capabilities, and upgrade URL.' It uses a specific verb ('get') and resource ('account status'), and distinguishes from sibling tools by focusing on account-level information rather than individual resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises to 'Call this FIRST when figuring out what features you have access to' and explains how to use the upgrade_url ('show it in chat when a feature requires a higher plan'). This provides clear when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation readOnlyHint=true already signals a safe read operation. The description adds that it returns daily page views for the last 30 days, which is useful but does not disclose other behavioral traits such as whether results are paginated or if historical data is mutable. The annotation carries the transparency burden, so a score of 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single clear sentence, front-loaded with key information. Every word is necessary and nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains what data is returned but leaves ambiguity: does it return data for all sites or a specific site? Without output schema details, the agent might not know the granularity. Given the tool's simplicity and the presence of an output schema, the description is adequate but could be more explicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With zero parameters and 100% schema coverage, the description does not need to provide parameter details. The baseline for no-parameter tools is 4, and the description adds no confusion.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns 'Daily page views per site for the last 30 days,' identifying the resource (analytics) and scope (last 30 days). However, it does not explicitly use a verb like 'retrieve' or 'get,' and it does not differentiate from siblings, though no close sibling exists.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of limitations or prerequisites, leaving the agent to infer usage context on its own.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses that it refreshes from Stripe on every call (potential side effect despite readOnlyHint). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences, front-loaded with core purpose, no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Explains all necessary context: status implications, included URLs, and refresh behavior. Output schema exists, so return fields need not be detailed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist; baseline 4 applies. Description adds no parameter info, but none needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description explicitly states return value (Stripe Connect state with enumerated statuses) and resource. It clearly distinguishes from sibling tools by focusing on Stripe Connect onboarding, which no sibling covers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Describes when to use: to check if user can list sites (status == 'ready' required). No explicit alternatives or when-not-to, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true, confirming it's a safe read operation. The description adds the behavior of returning null if no function is deployed, which is useful context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no wasted words. Every part is necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and only one simple parameter, the description is complete. It explains what is returned and the null case.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter 'slug' is fully described in the schema (100% coverage). The description does not add additional meaning beyond the schema's description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action: returning the deployed function source and metadata for a site, including the null case. It distinguishes from siblings like 'deploy_function' and 'get_function_logs'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving function details but does not explicitly state when to use it over alternatives like 'get_function_logs'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses key behavioral traits: 7-day retention, newest-first ordering, and the exact fields returned (timestamp, level, message, outcome, statusCode, requestId, CPU/wall time). It also mentions a Cloudflare dashboard deep-link. These details add value beyond the readOnlyHint annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a compact two sentences, with no wasted words. The first sentence covers the main purpose and constraints, the second elaborates on return data. It is appropriately front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (3 params, 1 required, output schema present), the description is complete. It explains what the tool does, when to use it, what the logs contain, and retention/ordering. No gaps remain for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so the baseline is 3. The description does not add parameter-specific meaning beyond the schema; it focuses on output details. While this is acceptable, there is no extra semantic enrichment for parameters like slug, limit, or since.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reads recent runtime logs for a site's per-site Worker, specifying the resource (function logs), action (read), and additional details (console output, request summaries, exceptions). It distinguishes itself from sibling tools like get_function or deploy_function by focusing on log retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this to debug a deployed function,' giving clear context. However, it does not provide negative guidance or mention when not to use this tool versus alternatives, though sibling tool names imply differentiation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already set readOnlyHint=true, so the read-only behavior is clear. The description adds that it includes specific fields, which is useful but does not disclose additional behavioral traits beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: the first explains the purpose and included data, the second provides usage guidance. Highly concise without superfluous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has one parameter, read-only annotations, an output schema, and the description covers purpose and usage, it is complete for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already fully describes the single parameter (id) with format and pattern. The description does not add further semantics, so it meets the baseline for 100% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reads a project by ID and lists the included fields (label, status, customer details, etc.), distinguishing it from sibling tools like list_projects or update_brief.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use before update_brief / regenerate_brief', providing clear context for when to use this tool. It does not explicitly mention when not to use it, but the guidance is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation declares readOnlyHint=true, and the description confirms a read operation (retrieving settings and version history). No additional behavioral traits (e.g., rate limits, specific permissions) are disclosed beyond what annotations provide. The description does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is front-loaded with the core purpose ('Site settings + version history'). Every word is necessary, and there is no redundancy. It is highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (one parameter, read-only, output schema exists), the description covers the essential purpose. It does not mention authentication or scoping, but these are typically assumed. The description is sufficiently complete for this level of complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage (slug is described). The description does not add any extra meaning or constraints for the parameter beyond the schema's 'site slug, e.g. my-site'. Baseline score is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it returns site settings and version history for one site. It implicitly uses the 'get' verb, and the resource 'site' is unambiguous. However, it does not differentiate from sibling tools like get_site_access or list_versions, but the combination of settings + version history provides enough specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. For example, it does not mention that list_sites should be used to enumerate sites, or that get_site_access is for access control. The description is purely declarative without usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true. Description adds context as counterpart to set_site_access and lists returned fields, but no additional behavioral details beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with colon-separated list and second clause. Concise, front-loaded, no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists (implied), description lists all returned fields clearly. Simple read tool with clear purpose and usage guidance; complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with slug described as 'owned site slug'. Description repeats 'owned site' but adds no new meaning beyond what schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Explicitly states reading an owned site's access policy with specific fields (mode, allowedEmails, etc.). Distinguishes from sibling set_site_access.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to use before changing access (check before setting) and identifies read-only counterpart to set_site_access, guiding when to use vs. alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the agent knows it is safe. The description adds behavioral context by specifying the consolidated nature and that it includes a computed verdict, which goes beyond the annotations. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: the first lists the components, the second gives a usage directive. It is front-loaded with the essential information and contains no fluff. Every sentence serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema, the description does not need to explain return values. It adequately describes the three components (page funnel, email events, verdict). The tool is simple with one parameter, and all necessary context is provided.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% as the only parameter 'testId' is well described in the schema. The description does not add extra meaning about the parameter beyond what the schema provides, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it returns a consolidated object with page funnel metrics, email events, and a computed verdict. The verb 'get' is implied, and the resource is test status. It distinguishes from siblings by emphasizing it is the single source for progress, contrasting with querying email separately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear guidance: use this tool as 'The single place to check progress' and advises against querying email separately. It does not explicitly mention when not to use it, but the context is clear enough for an agent to prioritize this over individual email queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description is consistent with the readOnlyHint annotation and adds no contradiction. It discloses the tool is for reading, but does not provide additional behavioral details beyond what annotations already cover.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences with no unnecessary words, effectively conveying the tool's purpose and usage context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters and an output schema is present, the description provides sufficient context. It explains the type of threads returned and when to use the tool, making it complete for this simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With zero parameters and 100% schema description coverage, the description adds no additional parameter meaning, which is acceptable. The baseline of 4 applies due to no parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns threads tagged as complaints or bounces, with a specific verb 'return' and resource 'threads'. The title reinforces this, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description advises to read these before any further sending, providing clear context for when to use the tool. However, it does not explicitly mention when not to use or suggest alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the tool is known to be read-only. The description adds the output format (path, schedule, lastRunAt), which is useful but not critical beyond annotations. No behavioral contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two succinct sentences: first sentence states the action, second sentence describes the output. No unnecessary words, achieving high conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple structure (1 param, output schema exists), the description sufficiently explains what the tool does and what each entry contains. However, it implicitly assumes a deployed function exists, which could be clarified, but overall it's complete enough.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the parameter 'slug' described as 'site slug whose cron triggers to list'. The tool description adds no new semantic meaning beyond the schema, fitting the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists cron triggers for a site's deployed function, specifying the verb 'list' and the resource ('cron triggers for a site'). It also describes the output format (path, schedule, lastRunAt), distinguishing it from sibling tools like set_cron or remove_cron.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like set_cron or remove_cron, or other list tools. The description is purely descriptive of the action without contextual usage advice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds behavioral context about the returned data structure (grouped subdomains with site, status, provider), which is useful beyond the annotation. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that is front-loaded and contains no redundant information. Every word contributes to defining the tool's output.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters and a read-only annotation, the description adequately covers the key output aspects. It does not mention pagination or ordering, but those are typically absent when no parameters are provided. An output schema exists to further clarify.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters in the schema, so the description cannot add parameter-level details. Baseline is 4 because with 0 parameters, the tool is self-explanatory.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'List' and resource 'custom domains' with details on grouping by subdomains, each subdomain's site and status, and detected provider. This clearly distinguishes from sibling tools like list_domains which likely returns a simpler list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance provided on when to use this tool versus alternatives such as list_domains or check_custom_domain. The description does not mention context or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description discloses that the output includes an id used to reach a per-database MCP server, and mentions the GET endpoint for further operations, adding valuable behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: the first provides the core function, the second explains usage context. Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description sufficiently covers what the tool does, when to use it, and the key output element (databaseId). No gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With zero parameters and 100% schema coverage, the description has no need to explain parameters. The baseline score of 4 applies as no additional parameter details are required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists SQL databases (D1 or Neon Postgres) including attached site, and explicitly distinguishes it from sibling tools like create_database or delete_database by positioning it as a prerequisite for db_query/db_schema operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It directly advises to call this tool BEFORE db_query/db_schema work to obtain a databaseId, and explains that those tools live on a separate per-database MCP server, providing clear workflow context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the description's mention of 'connected' and 'status' adds mild context. However, it does not explain what 'connected' means or provide other behavioral traits beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with no wasted words. It is appropriately sized for a simple list tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and no parameters, the description is fairly complete but lacks explanation of 'connected' status and does not mention any ordering or filtering. Minimal but not fully informative.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has no parameters, so baseline is 4. The description adds no parameter info, but it is not needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists connected custom domains with status. However, the presence of a sibling 'list_custom_domains' creates ambiguity about the difference, lowering the score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives like 'list_custom_domains' or when not to use it. The description lacks context for appropriate use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true, so the description adds value by specifying returned fields and optional filtering. This goes beyond the annotation without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the main purpose and quickly adds the optional filter. Every word contributes; no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists and the tool is simple (1 optional param), the description sufficiently covers purpose and filter. It could mention pagination or limits but is generally complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers the clientId parameter completely (100% coverage). The description merely restates the filtering behavior without adding new semantic detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'list' and the resource 'the user's private cloud Drives', specifying returned fields (id, name). It distinguishes from sibling tools like create_drive or drive_delete_file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions the optional clientId filter but does not explicitly state when to use this tool versus other list tools (e.g., list_databases, list_projects). Usage context is implied but not elaborated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the description's statement of listing is consistent. Beyond that, the description does not disclose additional behavioral traits (e.g., pagination behavior, rate limits) but adds context on thread types. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence that conveys the essential purpose and filter capability. Every word adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the existence of an output schema, the description does not need to explain return values. It sufficiently covers the tool's scope, filter, and context, making it complete for a list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The description mentions 'Filter by tag' but the schema's filter parameter with enum values already covers that. No additional meaning is added beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool lists the user's email inbox threads, specifying the types of threads (outbound demand-test sends, inbound replies, unsubscribes, complaints, bounces). This specific verb-resource-scope combination distinguishes it from siblings like list_site_inbox.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.