rocketsloth

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

Beyond the readOnlyHint annotation, the description adds that no authentication is needed and details what information is returned (application flow, integration model, etc.), providing comprehensive behavioral disclosure.

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 with a colon, conveying multiple aspects efficiently. It is front-loaded with the main purpose, but somewhat dense. Still clear and not overly verbose.

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 input parameters and no output schema, the description fully covers the tool's purpose and content. It addresses the key areas (flow, integration, payouts, catalog) and authentication requirements, 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 no parameters, and schema coverage is 100%. The description does not need to clarify parameters, and baseline for no parameters is 4. It does not add param-specific detail because none exist.

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 explains what Rocket Sloth is and how to use it, covering application flow, integration model, and payout terms. It is distinct from sibling tools which are specific (e.g., account, payments), so purpose is well-defined.

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 notes 'No authentication required' and implies this is for understanding the platform overview. While it does not explicitly exclude use cases, the sibling list provides contextual alternatives, so guidance is present but could be more explicit.

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 (destructiveHint=true), the description adds context about authentication, view being non-destructive, and specific destructive behaviors like token revocation.

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 front-loaded purpose and clear action breakdown. Every sentence is informative and 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?

Covers all parameters and actions, but lacks mention of return values. Given no output schema, a slight gap but still functionally complete for an 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 description adds meaning to the action parameter by listing options and their effects, and clarifies conditional use of agent_name and contact_email. Schema already covers parameters well.

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 views or updates the account, listing three specific actions. It is distinct from siblings but does not explicitly differentiate them.

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 via action descriptions but lacks explicit guidance on when to use this tool versus alternatives or when not to use it.

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 authentication requirement ('admin token') and explicitly states that sync action updates state ('update it'), consistent with readOnlyHint=false. 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?

Concise single sentence front-loaded with access control. Efficiently conveys key information, though the list of actions could be more 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?

Missing expected output format (e.g., what list returns, what sync returns), error conditions, and token format details. No output schema to compensate.

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 parameters have descriptions in the schema (100% coverage). The description restates the action options and links publisher_id to sync, but does not add significant 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?

Description clearly states two distinct actions: 'list pending applications' and 'sync (re-check live approval status)'. Verb+resource is specific, distinguishing from sibling tools like 'application_status' and 'apply'.

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?

Specifies 'Operator only (admin token)' as a usage prerequisite, but does not provide guidance on when to use this tool versus alternatives like 'application_status' or 'checklist'.

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=false, destructiveHint=false. The description expands by detailing that the tool can mutate settings ('adjust') and lists specific resources and actions. This adds useful behavioral context beyond the annotations, though it does not disclose potential side effects or permissions needed beyond authentication.

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, consisting of three sentences. The first sentence delivers the main purpose. The second provides usage guidance. The third lists specific resources and actions. No redundant information, and structure effectively prioritizes key info upfront.

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, no output schema, and nested objects, the description covers the essential usage pattern and examples. It lacks detail about return types or error handling, but the examples and guidance on 'call with no action' provide sufficient context for an agent to interact 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 input schema describes all 4 parameters with 100% coverage. The description adds value by explaining token authentication, the role of 'action' (omitting lists available actions), and the meaning of 'resource' with examples. This goes beyond the schema's generic 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?

The description clearly states the tool's purpose: 'View and adjust ad settings for your site'. It specifies the verb 'View and adjust' and the resource 'ad settings', and differentiates from sibling tools which are not ad-related. Examples of resources and actions provide concrete clarity.

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 authentication ('authenticate with your API token sk_...') and usage pattern ('Pass resource and action; call with no action to see what's available'). It does not explicitly state when not to use this tool or alternatives, but given the siblings are distinct, this 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?

Annotations indicate readOnlyHint=false and idempotentHint=false. The description adds specific non-obvious behavior: on first approval call, returns API token exactly once and upgrades units. 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?

The description is two concise sentences that efficiently convey purpose, usage, and key behavioral details with no redundant 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?

No output schema exists. The description explains the approval scenario return behavior but does not describe statuses or return format for pending/rejected states, leaving some 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 documentation is 100% covering the token parameter. The description adds value by specifying the token prefix format (at_...) and alternative Bearer header usage, going 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 checks an application's status using its token. It distinguishes from sibling tools like 'apply' or 'admin_applications' by focusing on status 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 implies usage when an application token is available and you want to know if approved. It does not explicitly mention when not to use it or compare to alternatives, but 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?

Beyond annotations (which indicate a write operation), the description discloses the token format, that units serve house creatives during review, and the rate limit per IP. It also clarifies no authentication is required, adding practical operational context not present in 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 front-loaded with the core purpose, followed by a concise summary of requirements, return value, immediate integration, and auth/rate-limit notes. Every sentence provides useful information without unnecessary verbosity.

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 no output schema, the description compensates by fully describing the token return and immediate next steps. It explains the application review context and live-site requirement, making the tool self-explanatory. The presence of sibling tools like application_status does not prevent 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?

Schema coverage is 100%, so the baseline is 3. The description restates which parameters are required vs optional but doesn't add details beyond the schema's own descriptions, such as the default behavior of google_email already being documented 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 opens with 'Apply to become a Rocket Sloth publisher' – a specific verb and resource. It is clearly distinct from siblings like application_status, which is about checking status. The token and immediate integration details further cement its 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: requirements, immediate integration after receiving the token, 'No authentication required', and rate limiting per IP. However, it doesn't explicitly name alternative tools like application_status for checking status, so it doesn't fully cover 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?

Beyond the annotations (readOnly, openWorld), the description adds meaningful behavioral details: 'No authentication required; rate limited per IP' and the instruction to 'Pass the returned thread_id on follow-up questions to keep context,' which reveals stateful conversation behavior. This adds value beyond the structured 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 with the core purpose, followed by essential follow-up instruction and access constraints. Every sentence earns its place 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?

The tool is a simple Q&A interface with low complexity. The description covers purpose, scope, conversation context, and access constraints. Annotations cover safety, and the schema fully documents parameters. No additional behavioral or output details are necessary for an agent to use it 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% for both params, so the baseline is 3. The description repeats the thread_id guidance already in the schema ('Pass the returned thread_id on follow-up questions'), adding no new semantic detail beyond what the schema provides. It doesn't compensate further, but doesn't need to due to full 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's purpose: 'Ask the Rocket Sloth setup agent anything about integration, ad units, application, reporting, or payments.' This specifies a verb ('ask'), a resource ('setup agent'), and a scope (topics), distinguishing it from sibling tools that perform specific actions like 'apply' or 'reclaim'.

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 use: it covers which topics to ask about and instructs to pass thread_id for follow-ups. It doesn't explicitly exclude alternatives or name sibling tools, but the domain scope and thread_id handling give clear practical usage guidance, meeting the 'clear context, no exclusions' level.

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 supplements the readOnlyHint annotation by detailing the return structure (statuses, actors, instructions, next_action) and authentication requirement, providing behavioral clarity 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 three sentences with no wasted words, front-loading the purpose and then adding details efficiently.

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 read-only tool with one parameter and no output schema, the description adequately covers what the tool returns, where it fits with siblings, and authentication 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 single parameter token is already described in the input schema with prefixes and header alternative. The description's repetition adds no new semantic value, so baseline 3 for 100% schema coverage 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 that the tool returns the onboarding checklist with statuses, actors, instructions, and next_action. It distinguishes itself from application_status by noting the checklist is embedded there, clarifying the tool's specialized scope.

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 advises that for the full checklist in context of application_status, one can use that sibling, but it does not explicitly state when to prefer this tool over others. It gives some guidance by mentioning the alternative location.

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 destructiveHint=false. Description adds valuable behavioral context: availability after apply, authentication methods, and the verify parameter's action (fetches site, confirms installation). This goes 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?

Two sentences with no wasted words. First sentence states core purpose and authentication; second adds optional verification. Front-loaded with key actions.

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 tool with 2 params and no output schema, the description is complete: it explains what is retrieved, how to authenticate, optional verification, and availability constraint. Lacks error cases or output format details, but not critical for this scope.

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 fully. Description adds meaning by specifying token formats (at_... or sk_...) and explaining that verify triggers site confirmation. This enhances understanding 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 tool retrieves the script tag, ad-unit markup, and placement guidance. It specifies authentication tokens and an optional verification step. The phrase 'Available immediately after apply' distinguishes it from sibling tools like 'apply' or 'checklist'.

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?

Description provides context on when to use (after applying) and how to authenticate but does not explicitly state when not to use or name alternatives among siblings. Usage guidance is present 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 already declare readOnlyHint=true, and the description adds behavioral details such as the need for authentication and the different action-specific outputs. 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 a single sentence, which is efficient, but the embedded authentication note and pipe-separated list make it slightly dense. Front-loaded with the main 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?

No output schema exists, so the description needs to explain return values. It does so for each action, listing key data like 'amount owed' for history and 'tax form status' for tax. Lacks details on response structure but is 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%, so baseline is 3. The description enriches parameter semantics by explaining what each action value returns (e.g., 'settings: payout method and threshold'), adding valuable context 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 is for viewing payout information and specifies the three actions (settings, history, tax). It distinguishes from sibling tools like 'account' or 'subscriptions' but could be more explicit about what sets it apart.

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 some usage context (e.g., authentication with API token) but does not explicitly state when to use this tool versus siblings, nor does it offer negative guidance 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?

The description clarifies the two-step verification flow and that the tool releases a previous registration. Annotations already indicate mutation (readOnlyHint=false) and non-destructive nature; the description adds detail about the required verification methods and that apply must be re-called, providing behavioral context beyond the 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 with no fluff, front-loads the main purpose, and is easy to scan.

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 covers the full workflow including prerequisites from apply, the two actions, and the post-condition. While it doesn't describe return values, the tool's purpose and invocation are clear. No output schema exists, but the description's step-by-step nature compensates.

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 all parameters with descriptions, but the description adds semantic meaning by explaining the sequence (action=start then action=verify with method) and how method relates to action. This is more than baseline, so a 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 states a specific action ('Free up a site that has an inactive previous registration') with a clear resource and condition. It differentiates from siblings like apply by referencing the scenario where apply fails.

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 the tool ('If apply says the site is already registered') and gives a step-by-step process involving action=start and action=verify, ending with calling apply again. This directly guides the agent on usage.

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 mark the tool as destructive, and the description elaborates by stating it 'revokes all old tokens' and returns fresh tokens. It also discloses that no authentication is required and that rate limiting applies per IP and site, adding valuable operational context beyond the 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: purpose, actionable workflow with both actions, and constraints (no auth, rate limits). No redundant phrasing; each sentence adds distinct 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?

Tool has two distinct actions and a conditional parameter, but the description fully specifies inputs, behavior, and outputs (fresh application/API token). No output schema exists, so the description rightly covers the return value and operational constraints.

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 all parameters with descriptions, so baseline is 3. The description clarifies the conditional relationship between action and code (code only used in confirm), and specifies that site_url must be previously registered with apply, adding workflow meaning not present in 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 opens with 'Recover access when application or API tokens are lost', clearly defining the tool's purpose and trigger condition. It then details the two action modes (start/confirm), distinguishing this recovery flow from sibling tools like apply or reclaim.

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 when to use the tool ('when application or API tokens are lost') and provides a two-step workflow (action=start then action=confirm). It does not explicitly compare with sibling alternatives like reclaim, but gives sufficient context for correct usage.

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 readOnlyHint=true and destructiveHint=false. The description adds authentication context (API token) but does not elaborate on additional behavioral nuances such as rate limits or authorization 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?

The description is a single, concise sentence that includes authentication hint, action list, and date format. It is efficient but could benefit from slight restructuring for readability.

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 tool lacks an output schema, and the description does not describe the result format or possible response structures. For a reporting tool, this omission leaves the agent without necessary context for handling responses.

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 parameters are documented in the input schema (100% coverage). The description repeats the list of action values and date format, adding no new details 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 tool provides revenue and traffic reporting for the user's account, listing specific report types. This distinguishes it from sibling tools like 'about' or 'account'.

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 does not explicitly guide when to use this tool versus alternatives among sibling tools. It implies usage for account-level reporting but lacks contextual 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 provide readOnlyHint=false and destructiveHint=false, but the description adds context about authentication and discovery. It does not elaborate on whether operations are mutating or their effects, so modest additional transparency.

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 completely front-loaded and efficient, with 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?

Schema covers all parameters, but no output schema exists. The tool has a nested object parameter and no required fields. The description covers the discovery pattern but lacks details on return values, error handling, or what 'manage' entails, so adequate but not thorough.

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. The description adds a usage pattern (discovery by omitting action) that goes beyond the schema's parameter descriptions, enhancing understanding.

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 manages 'reader subscriptions and donations' and mentions the resource/action pattern. It distinguishes from siblings like 'payments' implicitly but does not explicitly differentiate, so score 4.

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 instructions: authenticate with token sk_..., pass resource and action, and call without action for discovery. It does not mention when not to use or alternatives, but the guidance is clear and actionable.

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 authentication via API token and discovery mechanism. Annotations provide no readOnly/destructive hints, so description adds some context but doesn't mention side effects or operation idempotency.

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 paragraph, front-loaded with purpose, followed by examples. Each sentence contributes meaningful 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?

Covers authentication and discovery, but incomplete on return formats for actions besides embed. The 'params' open object lacks guidance on accepted parameters per action. No output schema, so description should compensate more.

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 100% (baseline 3). Description adds value by explaining the resource/action paradigm, discovery pattern, and specific purpose of 'resource=embed'. Examples clarify usage 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?

Description states 'Manage video monetization' and provides specific examples (player list, embed markup). Title aligns. However, 'manage' is generic and doesn't fully differentiate from sibling tools like 'payments'.

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?

Gives usage examples (resource=player action=list, resource=embed) and advises calling without action to discover resources. No explicit when-not-to-use or comparison with sibling tools.

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