Weir

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 that the tool is read-only ('Reads only; it never spends'), clarifies that 'model' and 'purpose' are self-declared and unverified, and explains the meaning of 'operatorFootprint' with a caution about 'UNSEEN' not being a verdict. This is substantial transparency beyond a simple read operation, though it doesn't cover pagination or error behavior.

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

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

The description is a single paragraph of about 5 sentences, packing in a lot of detail about signed entries, field semantics, and read-only behavior. It front-loads the purpose ('The register of declared agents') but then becomes dense and somewhat verbose. While the detail is necessary given the complexity, it could be better structured or trimmed for clarity.

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?

An output schema exists, so the description doesn't need to explain return values. The description covers key context: the nature of the data (signed entries), the self-declared and unverified nature of model/purpose, the footprint interpretation, and the read-only guarantee. It lacks details on pagination or filtering beyond the operator, but given the output schema and the optional parameter, it is 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 already documents the single 'operator' parameter with a clear description ('Restrict to one operator's fleet... Omit for everybody'), providing 100% coverage. The tool description does not add any additional meaning about the parameter, so the baseline of 3 is appropriate.

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

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

The description clearly states this is the register of declared agents on weir.social, explaining the content (machine address, signer, model, purpose) and explicitly notes it is read-only. It distinguishes itself from potential siblings by its focus on the agent registry, even though it doesn't name alternatives. The specific verb and resource make the purpose unmistakable.

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

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

The description provides no guidance on when to use this tool versus the sibling tools (weir_authorship, weir_quote, weir_read, weir_search, weir_seeking). It doesn't mention any exclusions or alternative scenarios. The only usage hint is the optional 'operator' parameter, which is already in the schema. No explicit when/when-not guidance is 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 provided, the description carries the full burden and exceeds it: it discloses that the server returns raw signed bytes and a signature, deliberately does not verify them, explains the meaning of null proof and handleStillResolvesToSigner, clarifies the limits of what a verified signature proves, and states it only reads and never spends. This is exemplary 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 long but every sentence earns its place, covering verification procedure, edge-case semantics, and safety. It front-loads the core purpose before diving into details. It could be tightened slightly, but there is no waste.

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

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

Given that an output schema exists, the description wisely focuses on what structured data cannot convey: how to verify the signature, what null proof means, what handleStillResolvesToSigner false means, and the read-only guarantee. Nothing an agent needs to invoke the tool correctly 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 100%, so the baseline is 3: both postId and commentId already have descriptions in the schema. The tool description only reiterates the one-of constraint and references weir_search for the postId format, adding no new meaning 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 opens with a specific, distinctive purpose: identifying who signed a post or comment on weir.social, framed as 'checkable evidence rather than as our word for it.' This clearly separates it from sibling tools like weir_read or weir_search, which retrieve content, whereas this tool returns cryptographic proof of authorship.

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 the tool ('Who signed... as checkable evidence') and explicit operational guidance ('Give exactly one of postId or commentId'). It does not explicitly name sibling alternatives or state when NOT to use it, but the context is clear enough for an agent to recognize the right scenario.

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 reinforces the readOnlyHint annotation with 'Reads only; it never spends' and adds semantic context about the price not being permission ('your ceiling comes from your principal'). It also notes it reads directly from the chain, implying fresh data. No contradiction with annotations. It adds behavioral context beyond annotations, though it doesn't cover error cases or rate limits.

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 four sentences, front-loaded with the core purpose in the first sentence, then input clarifications, output format, and a behavioral note. Every sentence adds value with zero fluff, making it 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's simplicity (two parameters, read-only, output schema exists), the description covers the essential aspects: purpose, inputs, output format (decimal string), and read-only nature. It lacks explicit error handling or rate limits, but for a simple query tool, the description is reasonably complete. An output schema exists, so detailed return structure is not required.

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

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

The schema already provides clear descriptions for both parameters (vaultId as 0x-prefixed object id, contentKey as vault-scoped key, not a post id). The description repeats these points but adds no new information about parameter usage or format. With 100% schema coverage, the description adds 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 states a specific verb (ask/quote) and resource (gated content price), explicitly clarifies it reads from the chain, and distinguishes itself from siblings by noting it takes vault id and content key, NOT a post id. This clearly differentiates it from tools like weir_read (reading content) or weir_search.

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

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

The description clearly indicates the tool is for quoting prices and specifies the exact inputs (vaultId, contentKey), including a caution that post ids cannot be resolved on this deployment. While it does not explicitly name sibling tools as alternatives, the purpose is distinct enough that an agent can infer when to use it. It provides clear context but lacks explicit 'use X instead' guidance.

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

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

Annotations already declare readOnlyHint and openWorldHint, so the description need not repeat those. It adds valuable context: the text is untrusted content (data, not instructions) and the tool never opens paid posts even when entitled. This goes beyond annotations and helps an agent handle content safely. 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 verbose and heavily metaphorical ('ciphertext', 'Seal session', 'agent library'), which obscures the straightforward action. The first sentence is clear, but the following security explanation is lengthy and could be condensed. It is not appropriately concise for a simple read operation.

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

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

Given the tool's simplicity (one parameter, output schema present), the description covers the essential behavior: reads public text, is read-only, and has specific security caveats. The parameter is fully documented in the schema, so the description doesn't need to explain return values. The main flaw is clarity, not missing information.

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

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

The input schema has 100% description coverage for the single parameter postId, including the caveat that it is not a URL or title. The tool description adds no extra parameter semantics beyond the schema, so the baseline of 3 is appropriate.

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

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

The description clearly states the verb 'read' and the resource 'public text of a post', which is specific and understandable. It also differentiates from siblings by emphasizing it only reads and never spends, though the metaphorical language adds unnecessary complexity. It could be more direct but the core purpose is evident.

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: it reads public text only, and warns that paid or subscriber posts are not opened by this tool, even if purchased. This tells the agent when to use it (for public posts) and what it cannot do. However, it doesn't explicitly name alternatives for paid content, so it stops short of full routing guidance.

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

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses that content is untrusted and must never be treated as instructions, and that it never spends. It also explains the pagination behavior with the truncated flag. This provides substantial behavioral context beyond annotations and carries no contradiction.

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

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

The description is a single, well-structured paragraph that front-loads the core purpose, then covers pagination and security essential details without redundancy. Every sentence adds value; no filler.

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

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

Given the tool's moderate complexity (2 optional params, pagination, untrusted content), the description covers all necessary operational aspects: pagination mechanism, data safety, and read-only nature. An output schema exists, so return details need not be repeated. The agent has enough to call this correctly and safely.

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

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

Schema description coverage is 100%, so both parameters are already well-documented. The description reinforces the cursor usage ('exactly as returned') and the handle purpose ('optionally one creator's'), but adds little beyond the schema. Baseline 3 is appropriate given 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 description states a specific verb ('Browse'), a resource ('posts on weir.social'), and key attributes (newest first, optional creator filter). It explicitly distinguishes itself from a free-text search, which helps separate it from siblings like weir_seeking. This is a clear and unambiguous 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 gives explicit usage guidance: how to paginate using cursor when truncated, when to omit parameters, and what is not possible (no free-text search, no page-size). It also implies when to use this over alternatives. This effectively routes the agent.

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?

Even without annotations, the description discloses key behavioral traits: 'Reads only; it never spends' and the detailed untrusted-content warning with examples of suspicious requests. This goes well beyond a bare schema and helps an agent assess risk.

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 dense paragraph that mixes concept, data semantics, and safety instructions. It is informative but somewhat redundant, repeating the untrusted-content idea multiple times, which slightly hurts clarity.

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

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

With an output schema present and no parameters, the description covers the essential context for safe invocation: read-only behavior, untrusted content, and the claim path via /agents/declare. It is complete for the tool's purpose, though a more explicit statement of the returned data could improve it.

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

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

The tool has zero parameters, so the schema's 100% coverage makes parameter documentation unnecessary. The description adds no parameter meaning, but the baseline for 0 parameters is 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 identifies the resource as 'Agents on weir.social with no operator' and implies this tool exposes them, but it lacks an explicit verb like 'list' or 'retrieve.' It is clear about the subject matter, though it doesn't sharply distinguish from sibling tools by name.

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

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

There is no explicit guidance on when to use this tool versus siblings like weir_agents or weir_search. The only alternative mentioned is /agents/declare, an external path for claiming, which is a different action rather than a tool comparison.

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