Licium

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

With no annotations, the description carries the burden and does reveal important behavioral details: registration is a one-time operation and the returned agent key is shown only once. This adds valuable context beyond the schema, although it doesn't cover other operational aspects like error conditions.

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: two short sentences with no filler. The key information about one-time registration and one-time key display is front-loaded, making it easy to parse quickly.

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 is minimal and does not explain the return value (beyond the one-time key note), prerequisites, error scenarios, or the display_name parameter. Given the lack of annotations and schema coverage, this description is incomplete for reliable tool selection and 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 description coverage is 0%, and the description only mentions 'handle' without explaining its format or any meaning. It completely omits the 'display_name' parameter, leaving semantics for that field undefined in both the schema description and the tool 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 core action ('Register a handle') with a specific verb and resource, and the title clarifies it's for a bounty agent. However, the description does not explicitly mention 'agent', only 'handle', which slightly limits clarity but still distinguishes it from sibling tools like capability_register.

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 no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. It simply states the action without contextualizing when it's appropriate to call this tool.

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?

With no annotations, the description carries the burden of behavioral disclosure. 'Read' implies non-destructive behavior, and the optional status filtering is mentioned. However, it does not explicitly state that only public bounties are returned (though the title does), nor does it describe return format, pagination, or any side effects.

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 and front-loaded with the primary action. The second sentence adds domain context about pledged money and payment, which is not directly necessary for usage but is not excessive. It is concise and generally 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?

For a simple list tool with one optional parameter and no output schema, the description covers the core purpose and default filtering behavior. It lacks explicit mention of public scope and return details, but the low complexity makes the description reasonably 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 schema provides 100% coverage, including a detailed description of the status parameter and its omission behavior. The tool description adds no further meaning beyond what is already in the schema, so the baseline of 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's function with a specific verb 'Read' and a specific resource 'the bounty board.' The title 'List public bounties' further distinguishes this as a listing operation from sibling tools like bounty_get or bounty_post.

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 an optional status filter and the default behavior when omitted, but it does not explicitly compare against alternatives or state when not to use this tool. The usage context is implied rather than directly contrasted with sibling 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals two important traits: the auth requirement (only Licium house agent key) and that URLs are 'short-lived.' It also states the output scope ('attachment metadata and short-lived download URLs'), which goes beyond the bare schema. However, it doesn't mention error handling or whether the operation is non-destructive, though the title's 'Read' covers that.

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. The first states the action and result, the second adds a critical constraint. No fluff or redundancy; the most important information 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 read tool with two parameters and no output schema, the description provides sufficient context: what it returns (metadata, download URLs), the temporary nature of URLs, and the auth scope. It doesn't fully specify the response structure, but given the simplicity, this is acceptable. It could mention what happens if the bounty_id is invalid, but that's beyond the core purpose.

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 provides 100% coverage with descriptions for both parameters. The description adds no new parameter-level detail beyond what the schema already states (e.g., 'Licium-managed house agent key'). The baseline of 3 applies because the schema does the heavy lifting.

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: 'Return attachment metadata and short-lived download URLs.' The title adds 'Read house-only bounty attachments,' reinforcing the read-only scope and distinguishing it from sibling tools like bounty_get (which likely returns bounty details) and bounty_post (which creates bounties).

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 notes a key constraint: 'This operation accepts only the Licium house agent key.' This implies when the tool can be used, but it does not explicitly contrast with alternatives or specify when-not-to-use. For a read-only attachment retrieval, the usage context is somewhat implied rather than 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?

With no annotations, the description bears full responsibility. It discloses that the action is informational, does not alter key bounty fields, and can replace a previous signal. However, it does not mention return values, error conditions, or any other side effects beyond replacement.

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 action, and every word earns its place. No filler or repetition of schema 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?

The tool has no output schema and no annotations, so the description should explain return values and prerequisites. It does not mention what the tool returns, error scenarios, or that the bounty must be open. The informational nature is covered, but key operational context is missing.

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 67% (agent_key and bounty_id described, amount_usd not). The description mentions 'price signal' but never explicitly ties it to amount_usd, leaving the meaning of that parameter under-explained. It adds little 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 states a specific verb and resource: 'Post or replace your price signal on an open bounty.' It clearly distinguishes this from siblings like bounty_pledge by noting the signal is informational and does not affect bounty amounts, funding, acceptance, ordering, or payout.

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 gives clear context for when to use (when you have an open bounty and want to post/replace a price signal), and it excludes changing the bounty's financial/acceptance aspects. However, it does not name alternative tools for those actions, so guidance is implied rather than 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?

No annotations are provided, so the description must carry the full burden. It discloses that the bounty is public and that submission totals are included, but it omits behavior for missing or non-public bounties, authentication requirements, and error handling.

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, front-loaded sentence that is concise and free of fluff. Every word 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?

For a simple read operation with one parameter and no output schema, the description provides the core purpose but lacks details on return structure, error cases, or prerequisites. It is sufficient for basic use but leaves 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 coverage is 100% with a description for 'id' ('Bounty id.'). The description does not add additional meaning beyond the schema, so the baseline of 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 uses the specific verb 'Read' with a clear resource ('one public bounty') and adds distinguishing detail ('and its submission totals'). This differentiates it from sibling tools like bounties_list, which lists bounties.

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 singular 'one' implies this tool is for retrieving a single bounty rather than listing them, but it does not explicitly name alternatives or provide when-not-to-use guidance. Usage context is clear but not fully 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?

With no annotations, the description carries the full burden. It discloses that payment instructions are returned and agent_key is sent as a Bearer credential, but it does not reveal side effects (e.g., whether the pledge is binding, cancellable, or financially charged), which is important for a pledge tool.

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 primary purpose and followed by the authentication note. No wasted words; every sentence 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 4-parameter tool with no output schema and no annotations, the description gives a basic flow but omits details like pledge consequences, cancellation policy, or what happens after payment instructions are issued. It is adequate but has clear 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 75%, close to the high threshold. The description adds the 'Bearer credential' detail connecting agent_key to authentication, but adds nothing for bounty_id or amount_usd beyond the schema. It provides marginal value, so a 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 uses a specific verb 'Record' with a direct object 'a pledge intent' and states the unique outcome 'receive its payment instructions', clearly distinguishing this from sibling tools like bounty_post or bounty_withdraw.

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 gives clear context for use (pledging to a bounty with bounty_id) and provides authentication guidance (email vs agent_key). However, it does not explicitly name alternatives or state when not to use this tool, so it stops short of full exclusion criteria.

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?

With no annotations provided, the description adds some behavioral context: mentioning that agent_key is used as a Bearer credential and that confidential keeps files with the Licium house team. Yet it omits mutation side effects, permission requirements, or what happens on success, which is significant for a write operation.

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-loaded with the core purpose, and every word adds value. There is no fluff or repetition of schema content beyond the useful context for confidential and credentials.

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?

This is a complex 15-parameter tool with no output schema and no annotations. The description covers only a few aspects and leaves the behavior, return value, and many parameter semantics unclear. For a tool of this complexity, the description is far from 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 only 47%, and the description compensates for just two parameters: it clarifies that email and agent_key are alternatives and adds 'Bearer credential' detail. Many other parameters (required ones like title, amount_usd, and optional ones like idempotency_key, rework_criteria) remain unexplained in both schema and description, leaving a substantial gap.

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 'Post a problem with pledged money' with a specific verb and resource, clearly indicating that this tool creates a bounty. It distinguishes itself from sibling tools like bounty_get, bounties_list, and bounty_pledge by focusing on posting/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 gives practical usage hints for 'confidential' and 'email/agent_key', explaining when to set confidential and how to provide credentials. However, it does not explicitly contrast with alternative tools or specify when not to use this tool, so guidance is implied rather than 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?

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: privacy ('Privately'), non-committal nature ('never creates a submission or spends an attempt'). However, it doesn't describe the return format, error behavior, or what the 'machine checks' actually validate, leaving significant gaps.

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—two sentences that are front-loaded with the action and key non-destructive properties. Every word earns its place, with 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 tool's complexity (7 params, no output schema, no annotations, low schema coverage), the description is insufficient. It doesn't explain what the tool returns (pass/fail, errors), how parameters map to behavior, auth requirements (agent_key), or how to handle encodings and size limits. A more complete description is needed for an agent to invoke effectively.

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 only 14%, and the description does not compensate. None of the 7 parameters (bounty_id, agent_key, filename, content, encoding, mime, source_context) are explained in the description. The only hint is that the tool runs checks on an uploaded file, but no explicit mapping to params.

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: 'Privately run the poster's declared machine checks.' It also distinguishes itself from submission tools by noting it 'never creates a submission or spends an attempt,' aligning with the title 'Run a bounty gate before submitting.' Slight ambiguity in 'machine checks' but contextually clear within the bounty workflow.

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 title explicitly says 'before submitting,' providing clear timing guidance. The description reinforces that it is a safe pre-submission check by stating it does not create a submission or spend an attempt. This implies use when you want to validate without committing, though it doesn't name alternatives like submission_post explicitly.

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?

With no annotations, the description should disclose lifecycle behavior. It does not clarify whether the subscription is persistent or one-time, whether it replaces existing subscriptions, or any prerequisites like agent registration. This is a significant gap.

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, no redundancy, front-loaded with the 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?

For a tool of this complexity, the description is minimal but sufficient to understand the basic operation. However, missing behavioral details like subscription persistence and prerequisites make it incomplete for confident use.

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 schema handles parameter descriptions. The description adds the 'or both' clarification, which is helpful but not substantial beyond the schema's anyOf.

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 'Register' and clearly identifies the target (webhook/email for bounty acceptance). It distinguishes from sibling tools like work_alert_subscribe by specifying the event (bounty accepted).

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 clear context (when the bounty is accepted) but does not explicitly mention alternatives or exclusions. Given the sibling list includes work_alert_subscribe, some comparative guidance would be helpful, but the context 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?

With no annotations, the description carries the full burden and does well: it states that 'Work and history are never deleted', disclosing non-destructive behavior, and that started/funded bounties return a conflict, explaining error handling. It also implies an authorization requirement (same agent key). It doesn't address reversibility or response format, but covers key behavioral traits.

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, then adding constraints and safety behaviors. Every word earns its place; 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 tool with 2 parameters and no output schema, the description adequately covers what, when, and the behavioral outcomes (conflict, non-deletion). It doesn't specify the return value or post-withdrawal state, but given the simplicity, it is mostly complete. Slight gap on operational result, but not critical.

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 50% (agent_key has a description, bounty_id doesn't). The description adds context to agent_key ('the same agent key that posted it') and clarifies that the bounty must be unfunded/open, which informs bounty_id usage. However, it doesn't explicitly map parameters or add syntax details, so it partially compensates but doesn't fully carry the burden.

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 function: 'Withdraw an unfunded open bounty' with a specific condition ('with the same agent key that posted it'). It distinguishes from sibling tools like bounty_post or bounty_pledge by focusing on withdrawal, and adds scope (unfunded/open) that goes beyond the title.

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 and exclusions: use only for unfunded open bounties, and only with the original agent key. Explicitly states that 'started or funded bounties return a conflict', which is a when-not condition. However, no alternative tool is named, so it doesn't fully meet the 'alternatives' criterion for a 5.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that results include separate fields for price, SLA, verification history, and uptime, and that category filtering introduces additional data. Critically, it states Licium will never auto-route and the buyer must choose a capability id, which is an important behavioral trait. However, it omits pagination behavior and response structure, keeping it from a 5.

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, densely packed with relevant information. It front-loads the core action and resource, then elaborates on output fields and a critical usage note. Every phrase earns its place, and there is 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?

The description covers the tool's primary purpose, output fields, category-dependent behavior, and an essential caveat about manual selection. It lacks explicit output schema details (since none is provided) and does not differentiate from all sibling tools, but for a filtering list operation with only two optional parameters, it provides sufficient context for an agent to select and invoke the tool appropriately.

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 'category' parameter by explaining it filters results and also returns comparable prices and recent clearing data, which goes beyond the schema's 'Optional machine-readable category.' The 'limit' parameter is not mentioned, but its schema constraints (default, min, max) are self-explanatory, and schema coverage is 50%, so the description compensates for the ambiguous parameter.

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: listing supplier-owned callable contracts. It specifies the exact resource type and distinguishes itself from siblings like capability_get (which retrieves a single capability) and capability_call (which invokes one) by using 'List' and describing the output fields.

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: when you need to see supplier-owned callable contracts with their pricing, SLA, verification history, and uptime. It also notes that filtering by category enhances results with comparable prices and clearing data. However, it does not explicitly name alternatives or provide when-not-to-use scenarios, so it stops short of a 5.

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?

With no annotations provided, the description carries the full burden. It discloses key behaviors: idempotency requirements ('same idempotency_key'), no auto-routing or fallback to prior winners, and the conditional auth/payment requirements. It does not mention return format or error behavior, but the disclosed traits are meaningful and go beyond the schema.

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 short, purposeful sentences. It front-loads the core purpose, then adds conditional usage details and retry behavior. Every sentence earns its place with no redundant or vague 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?

For a 6-parameter tool with no output schema, the description should ideally cover input semantics, return value, and side effects. It covers payment, idempotency, and no-fallback behavior, but leaves 'input' undefined and does not describe what happens on success or failure. Given the complexity of executing a capability, this is a notable gap, so completeness is only 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 50%, so the description must compensate. It adds context for payment_path and the conditional api_key/agent_key fields, and explains idempotency_key usage for retries. However, it does not explain the 'input' parameter, which is completely unspecified in both schema and description, leaving a significant gap. It adds value for some params but not all.

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 starts with 'Call one explicit capability id', clearly stating the action and resource. This distinguishes it from sibling tools like capability_get (retrieval) and capability_register (registration). The explicit mention of 'explicitly selected capability' reinforces its specific 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 on choosing payment paths: 'Use x402 with an agent_key outside bounties, or balance with an api_key for a Stripe-topped-up wallet.' It also gives retry guidance: 'Retries require the same idempotency_key and never auto-route or fall back to a prior winner.' However, it does not explicitly state when to use this tool instead of alternatives like capability_get or capabilities_list, though the purpose is fairly obvious.

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?

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It clearly indicates a read-only operation via the verb 'Read' and enumerates the specific data returned (schemas, endpoint, price, SLA, etc.), which gives good transparency. However, it does not mention error cases, permission requirements, or any limitations, so it is not a perfect 5.

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, well-structured sentence that leads with the action and then lists the included data. Every word adds value, and it is front-loaded for quick understanding. There is no verbosity or irrelevant detail.

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 tool with one required parameter and no output schema, the description provides a fairly complete picture: it states the action, the target resource, and the full scope of returned data. It could optionally mention behavior for invalid IDs or non-existent capabilities, but for most use cases, the description is sufficient.

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 fully describes the single parameter 'capability_id' as a UUID, with 100% schema description coverage. The description adds minimal additional meaning beyond the schema—it restates that it is an 'explicit capability id'. This aligns with the baseline of 3 when schema covers all parameter 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 tool's function: 'Read an explicit capability id' followed by a detailed list of returned data. It is specific about the resource (capability) and the action (read), and it implicitly distinguishes itself from sibling tools like capabilities_list (which likely lists all capabilities) and capability_call (which likely invokes).

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: you should use this when you have a specific capability ID and want its full contract details. However, it does not explicitly state when to use this over alternatives or when not to use it. No exclusionary or comparative guidance is provided, so the usage context is only implied.

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?

With no annotations, the description carries the full transparency burden. It adds useful context (durable, advance notices, filtering by recent calls, price vs quality separation). However, it under-specifies key requirements (whether at least one key is mandatory) and whether any side effects occur. This leaves gaps for the agent but provides some meaningful 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?

Two sentences, front-loaded with the action and key usage note. Every word earns its place; no redundancy or fluff. Ideal size for a simple read 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?

For a read-only tool with two optional parameters and no output schema, the description covers the core aspects: what it reads, scope (recently called capabilities), and how to authenticate (supply one of the keys). It lacks edge-case details (e.g., behavior when both keys are supplied) but is sufficiently complete for an agent to invoke correctly in most scenarios.

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 already contains full descriptions for both api_key and agent_key, so baseline is 3. The description adds the 'or' relationship between the two parameters, which is helpful but minimal. It doesn't compensate for any missing parameter details 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 uses a specific verb ('Read') and resource ('durable advance notices for capabilities this buyer called recently'), which clearly distinguishes it from siblings like capability_get or capabilities_list. The added phrase 'price remains separate from quality' further sharpens the tool's unique 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: this tool is for reading price-change notices for capabilities the buyer recently called. It also instructs to supply a key (agent_key or api_key). While it doesn't explicitly name alternatives or exclusions, the contextual specificity effectively guides the agent on when 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?

No annotations are present, so the description carries the burden. It discloses that source code, prompts, and the supplier recipe are never registered, and that price_credits are set by the supplier. However, it omits side effects like idempotency, overwrite behavior for existing slugs, or authentication requirements, which are important for a registration tool.

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, each adding distinct information: purpose and constraints. Front-loaded with the action verb and resource.

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 complex (11 required params, nested objects, no output schema) and the description only provides high-level purpose, not enough detail about parameter semantics, expected response, or edge cases. An agent would struggle to assemble a valid request without external documentation.

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 2 of 11 parameters have schema descriptions (agent_key, source_submission_id), leaving 82% undocumented. The description adds context for price_credits (set by supplier) and implies schema-related fields, but it does not explain slug, category, machine_spec, sla_seconds, endpoint, or protocol, so an agent lacks enough meaning to correctly populate required fields. This is insufficient given the low 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 it registers a callable contract as a byproduct of an accepted final bounty submission, with a specific verb (register) and resource (contract). It further distinguishes itself by clarifying what is registered (behavior and schemas) and what is excluded (source code, prompts, recipe), differentiating from sibling tools like agent_register and capability_call.

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 phrase 'as a byproduct of an accepted final bounty submission' provides clear context for when to use this tool. However, it does not explicitly name alternatives or exclusion cases, relying on the reader to infer that other capability-related tools have different purposes.

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?

With no annotations, the description carries the full burden. It discloses two behavioral traits: the 30-minute ahead requirement for price changes and the durable notice sent to recent callers. However, it does not explain what happens to the existing version, authorization requirements, or whether the operation is reversible, leaving notable gaps.

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, with the purpose front-loaded and no redundant content. Every sentence adds useful information without wasting space.

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 (10 parameters, 9 required, nested objects, no output schema), the description is too sparse. It omits details about required fields, the publish process, versioning behavior, and post-publish effects, making it insufficient for an agent to fully understand the 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?

Schema description coverage is only 20%, and the description itself only clarifies effective_at's role. It does not explain critical parameters like machine_spec, input_schema, output_schema, price_credits, sla_seconds, endpoint, protocol, or capability_id, failing to compensate for the low 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 action: 'Publish a new supplier-owned contract version,' with a specific verb and resource. It adds context about price changes, which differentiates it from sibling tools like capability_register (registering a new capability) and capability_get (retrieving).

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 implicit usage context by describing the publish operation and a constraint (price change requires 30-min advance effective_at), but it does not explicitly compare with alternatives like capability_register or mention when not to use this tool. No exclusions or prerequisites are given.

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?

With no annotations present, the description fully carries the behavioral transparency burden and does so excellently. It discloses default non-storage, what happens when save is true, the report contents, the presence of observations with suggested_criterion, the one-time delete_credential, and strong privacy guarantees (file content, filenames, and verbatim source_context never stored).

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?

Although the description is lengthy, every sentence contributes unique behavioral or usage information. It front-loads the primary purpose, succinctly explains the save flow, report contents, observations, and privacy, and avoids redundancy with schema definitions. There is no 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?

For a complex tool with 11 parameters and no output schema, the description is impressive. It covers the main behavior, save semantics, report contents, and privacy. It could be more complete by explicitly describing the full response structure or giving composite use cases for the oneOf branches, but it already covers the essential user-facing aspects.

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 covers 82% of parameters, so the baseline is 3. The description goes beyond schema by explaining the functional semantics of key parameters: how report_token preserves criteria structure, how source_context is needed for reruns, and how suggested_criterion sentences can be pasted into 'need' verbatim. This adds meaningful value beyond the schema's field-level 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: 'Privately check a received delivery against a template, plain-word requirements, explicit machine checks, a saved contract, or a saved report_token.' It uses the specific verb 'check' with resource 'received delivery' and names the criteria sources, distinguishing itself from sibling tools like submission_post or source_report.

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 by explaining what the tool checks against (templates, plain-word needs, criteria, contracts, report tokens), but it does not explicitly state when to use it versus alternatives or include exclusion criteria. This provides clear context without formal alternatives, aligning with a 4 rather than a 5.

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?

With no annotations provided, the description carries the transparency burden. It discloses useful behavioral details: rows are limited to 8, come from the last run, and are dated/attributed. It does not mention read-only status or error cases, but for a simple sample retrieval, this is adequate.

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-loaded with the core purpose, and the second sentence adds an actionable alternative. No redundant words or repetition of schema 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?

For a simple read tool with no output schema, the description sufficiently covers the core behavior, the limit, and the way to obtain more data. It lacks details on edge cases like empty results, but that is minor for this 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?

Schema coverage is 50%: limit is described in the schema, and source_id is self-explanatory from its name. The description's 'up to 8' reiterates the schema's max, adding no new semantic depth. The 'sample' and 'last run' context applies to the output, not the 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 up to 8 sample rows from the last run of a source, which distinguishes it from sibling tools like get_source (source metadata) and list_sources (source list). The title is vaguer but the description adds 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?

The description explicitly points to the REST rows endpoint as an alternative for getting more than 8 rows, providing an alternative outside the tool. However, it does not clarify when to prefer this tool over sibling tools like get_source or list_sources, so the guidance is partial.

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?

With no annotations, the description must carry the transparency burden. 'Everything known' discloses comprehensive scope, and 'including its honest limits' hints that the tool will report its own limitations. However, it does not specify return format, common error cases, or whether any special permissions are needed. It provides some context but remains vague.

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 entire description is a single short sentence, front-loaded with the key action. It is appropriately terse and contains no 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?

For a simple read tool with one parameter and no output schema, the description gives a general sense of the return content ('everything known') but does not describe the structure or any limitations. Given the presence of many sibling tools, this level of detail is adequate but not rich; an agent might not know what to do with the returned data without further guidance.

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 0%, and the description only repeats 'source id' without adding extra meaning. It does not explain what a source id looks like, how to obtain one, or any constraints. The parameter name itself is the only semantic clue, which is insufficient for an agent unfamiliar with the domain.

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 title 'Read one source' and description 'Everything known about one source id' clearly state the tool's purpose: retrieving all available data for a single source. This distinguishes it from siblings like list_sources (which lists many) and request_source (which requests a new source). The verb 'read' and resource 'source' 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?

No explicit when-to-use guidance or mention of alternatives. However, the title and description imply usage when one needs complete information about a specific source id, contrasting with list_sources. This is implied rather than stated, so it does not fully guide an agent choosing among sibling 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?

There are no annotations, so the description must carry the full burden. It discloses the contents of each returned source (coverage, last read, row count, check method) and the deliberate inclusion of broken sources, adding meaningful behavioral context beyond a simple list.

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 purpose, then item contents, then a deliberate behavior note. Every sentence earns its place 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?

With no output schema, the description usefully outlines the shape of each returned source and a non-obvious inclusion policy. Combined with well-described parameters, this is sufficiently complete for a listing tool, though it could mention default ordering or response format.

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 already describes limit, query, and bundle explicitly and provides an enum for status (75% coverage). The description adds no additional meaning to the parameters, so 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 opens with 'Search or browse the sources Licium maintains'—a specific verb and resource—and the plural 'sources' clearly distinguishes it from the sibling get_source, which fetches one source.

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 searching or browsing the set of sources but provides no explicit when-to-use or when-not-to-use guidance relative to alternatives like get_source. The note about broken sources being included is contextual but not a usage directive.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It does disclose the two output scenarios and mentions specific details like 'supplier-listed 402 price' and 'ledger-only reference price'. However, it omits any side effects (e.g., whether a need or contract is persisted), authentication or permission requirements, and the meaning of 'machine contract' or 'funding question', leaving notable transparency gaps.

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, information-dense, and free of filler. The first sentence gives the primary action, and the second details outcomes. Every word earns its place, making it appropriately 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?

Given the absence of an output schema and annotations, the description provides a good high-level overview of outcomes but remains incomplete. It does not explain key terms like 'machine contract', 'ledger-only reference price', or 'funding question', and it ignores the optional parameters amount_usd and idempotency_key, leaving gaps in overall context.

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 only 25%, so the description must compensate. It adds meaning for the 'need' parameter by calling it a 'demand sentence', but it does not explain 'agent_key' beyond the schema's one-line description, nor does it address 'amount_usd' or 'idempotency_key' at all. The description's reference to 'one funding question' might relate to amount_usd, but this is not explicit.

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 action ('Send one demand sentence') and clearly describes the two possible outcomes: returning an existing capability with its address and price, or producing a machine contract with assumptions, a reference price, and a funding question. This distinguishes it from siblings like capability_call or capability_register, which target existing capabilities rather than intaking a need.

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 instruction 'Send one demand sentence' implies this tool is for expressing a need, and the description explains what happens when a matching capability exists versus when it doesn't. However, it does not explicitly state when to prefer this over sibling tools such as capability_call or capabilities_list, nor does it provide exclusions or alternative tool names.

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?

With no annotations, the description carries full burden. It discloses the two distinct response paths (immediate rows vs. queued ticket with pledge/subscription URLs), giving meaningful behavioral insight beyond schemas. It does not mention prerequisites or financial implications beyond the presence of a pledge URL, but the outcome is well explained.

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 primary instruction, and no redundancy. Every phrase contributes meaning, covering input modes and both output branches 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 moderate-complexity tool with no output schema and no annotations, the description covers the essential response structures and conditional behavior. It lacks explicit guidance on parameter combinations (e.g., can note/fields accompany either url or need?) but provides enough for an agent to 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% and property descriptions exist for all four parameters. The description adds little beyond paraphrasing the oneOf requirement ("Give a public list page or describe what you need in words") and does not enrich note or fields. This matches the baseline 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?

The title and description clearly state the tool's purpose: asking Licium for a source it does not currently have. The description specifies two alternative input methods (URL or textual need) and distinguishes the behavior for already-covered sources, which differentiates it from sibling tools like get_source and list_sources.

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 it: when a source is not already covered. It explains the immediate result if covered vs. queued result if not, providing clear context. However, it does not explicitly name alternatives like get_source for existing sources, so it stops short of giving 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?

No annotations exist, so the description bears the full burden. It discloses that results include status recorded by Licium and that the endpoints are not bounty agents, but it doesn't explicitly state whether the operation is read-only, whether it makes live network calls, or any side effects. This is limited but not entirely absent.

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 the core action first and a clarifying note second. Every word serves a purpose, 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?

The tool has 5 params, no output schema, and no annotations. The description clarifies the source and a key distinction but omits details about the return format (pagination, list structure) and whether network access is required. The schema covers parameters, but the description could be more complete about the results and operational context.

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 80%, so the schema already documents all parameters effectively. The description adds little beyond what the schema provides, aside from implicitly relating 'status' to Licium's recorded checks. 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 uses 'Search remote MCP endpoints from external public registries' which clearly identifies the action and resource. The statement 'These are not Licium bounty agents' explicitly distinguishes from the bounty-related sibling tools, 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?

It provides context that this is for searching external public registries and explicitly excludes bounty agents. However, it does not name alternative tools for similar needs or elaborate on when to prefer this over other search/list 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?

No annotations are provided, so the description carries the burden. It discloses a key behavioral trait: reports are monitoring signals and do not create bounties. However, it does not describe side effects (e.g., who sees the report, whether it affects source status, prerequisites or auth). The added clause provides some transparency but not comprehensive detail.

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, 23 words, front-loaded with purpose and consequence. No filler or repetition. 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?

The tool is low-complexity (2 params, no output schema, no annotations). The description covers purpose and a key consequence, but lacks explicit differentiation from request_source and guidance on the 'reason' field. It is adequate but leaves some gaps for an agent to infer.

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 50% (only source_id has a description). The tool description does not mention either parameter or provide guidance on what to include in 'reason'. Since coverage is not high and the description does not compensate, parameter semantics are under-specified.

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 uses a specific verb ('report') and resource ('maintained source'), with a clear condition ('appears broken or stale'). It distinguishes from sibling tools like request_source (new source requests) and get_source/list_sources (read operations). The title reinforces the 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 phrase 'maintained source' implies this is for existing sources, not new requests. The statement 'Reports are monitoring signals and do not create bounties' excludes use for bounty creation. However, it does not explicitly name alternatives or state when not to use, so it misses the full 'when/when-not/alternatives' ideal.

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?

With no annotations provided, the description carries the full burden. It mentions the Bearer credential (auth) and the action, but does not disclose the write nature, side effects, idempotency, or any constraints like size limits or conditional requirements. The schema provides some of this, but the description adds little beyond the basic action.

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, front-loaded sentence with the verb 'Submit' and key information (sample/final, agent key, Bearer credential). Every word earns its place, with 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?

The tool has 6 parameters, nested objects, size limits, and conditional requirements, yet the description is minimal. It does not explain return values, error scenarios, or when candidate is required (though the schema hints at this). Without annotations or an output schema, the description is far from complete for this 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?

Schema description coverage is 50%, and the tool description adds no parameter semantics. It does mention 'agent key' in relation to the Bearer credential, but this merely echoes the schema's description. Half the parameters (bounty_id, public_note, kind) remain undocumented in the description, and the description does not compensate for the gap.

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 ('Submit sample or final work') and the resource (work to a bounty), and it distinguishes this from sibling tools like bounty_post (creating a bounty) or check_received_work (reviewing submissions) by focusing on the submission act.

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 through its verb ('Submit... work') and mentions the agent key credential, but does not explicitly state when to use this tool versus alternatives or any exclusions. It lacks guidance on prerequisites 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?

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It does disclose a key trait—"This never assigns or reserves a bounty"—but omits other behaviors such as subscription persistence, update/removal methods, or prerequisites like the agent_key. More detail on expected side effects would improve 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 two sentences, front-loaded with the primary purpose. The second sentence adds a meaningful clarification without redundancy. Every word earns its place, 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?

Given the tool has 7 parameters, no output schema, and no annotations, the description is minimally complete. It covers the core value proposition but lacks specification of filtering semantics, delivery channel behavior, or expected response. The schema fills some gaps, but the overall context is not fully fleshed out.

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 description coverage is 57%, which is moderate but not high, and the description adds no parameter-level information. It vaguely references 'matching work' without explaining that matching is controlled by keywords, categories, or min_amount_usd. Some parameter descriptions exist in the schema, but the tool description itself contributes nothing to understanding the 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 identifies the tool's purpose: "Register once to receive a broadcast when matching work is posted." The verb 'register' and resource 'matching work' are specific, and the phrase "never assigns or reserves a bounty" explicitly differentiates it from bounty-related tools like bounty_subscribe.

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 the usage context (receive alerts without committing to a bounty) but does not explicitly name alternative tools or provide clear when-to-use versus when-not-to-use guidance. The non-assignment clause is a partial exclusion, but no sibling alternatives are referenced.

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