WORKS Public Verifier

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds some context about the return value ('pinned contract digest and scope') and the strict input requirements, but does not disclose additional behavioral traits such as side effects, rate limits, or failure modes. With annotations present, this is adequate but not exceptional.

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 with a clear front-loaded action and concise exclusions. Every word adds value, avoiding redundancy or filler. It is well-structured for quick parsing.

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

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

Given the tool has an output schema (so return values are documented) and annotations cover safety, the description is quite complete. It clearly states prerequisites and exclusions. However, the lack of parameter explanation is a minor gap that prevents a perfect score, as the agent must infer the meaning of 'contract' from enums alone.

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 has only one parameter 'contract' with an enum but no descriptions, and schema description coverage is 0%. The tool description does not explain what 'contract' means or how to choose between 'node-package' and 'env-safety'. The phrase 'matching supported static claim' hints at the concept, but the description fails to compensate for the lack of schema documentation, leaving the agent without clear 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: 'return the pinned contract digest and scope' given a public repository, exact commit SHA, and supported static claim. It also differentiates from siblings by explicitly listing what it does not handle ('runtime, builds, tests, deployments'), distinguishing it from other tools like eligibility or verification.

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

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

The description provides explicit preconditions ('After a task is already known to have a public GitHub repository, an exact lowercase 40-character commit SHA, and a matching supported static claim') and explicit exclusions ('Do not call for mutable or abbreviated refs, local or private repositories, runtime, builds, tests, deployments, or broad production-readiness claims'). This gives clear when-to-use and when-not-to-use guidance, even without naming sibling tools directly.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description adds crucial behavior: it is 'fast deterministic', 'does not download a repository or persist data', and instructs to halt on false eligibility. These go beyond the annotations and give the agent concrete expectations.

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?

Four short sentences, each with clear purpose: nature of tool, when to call, side-effect guarantee, and stop condition. Front-loaded with 'Fast deterministic preflight' and no redundant words.

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

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

The description covers purpose, usage context, side effects, and control flow. Since an output schema exists, it doesn't need to explain return values. The guidance is sufficient for an agent to decide when to invoke and what to do with a false result.

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

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

Schema description coverage is 100%, so the schema fully documents all parameters, including enums for claim, source_kind, and repository_visibility. The description adds contextual guidance about which parameter values matter (e.g., abbreviated refs, private repos) but does not add syntax or format details, so it stays at the baseline for high coverage.

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

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

The description identifies the tool as a 'preflight' eligibility check and states it should be called before any other WORKS tool, clearly distinguishing it from the sibling verification and lint tools. It names the specific resources (mutable/abbreviated refs, local/private repositories, claim types) it handles.

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

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

Explicitly instructs when to use this tool: before any other WORKS tool when eligibility is uncertain, with specific scenarios listed (mutable/abbreviated refs, local/private repos, build/test/runtime/deployment/production claims). Also provides a clear stop condition: 'If eligible is false, stop without calling verification.'

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 mark the tool read-only, idempotent, and non-destructive. The description adds significant behavioral context: it downloads a snapshot, runs a static contract without executing repository commands, and returns a signed receipt. It also instructs to return the report field verbatim and stop, which is valuable beyond the annotations.

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

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

The description is two sentences, front-loaded with the prerequisite, then the action, then the output directive. Every sentence serves a purpose, with no redundancy or filler.

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

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

The description covers the full workflow: precondition (eligibility), operation (download, run static contract), safety constraint (no commands), and output behavior (signed receipt, return report verbatim). Since an output schema exists, return-value details are not needed. It also references the sibling tool appropriately, providing complete contextual 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?

With 0% schema description coverage, the description compensates by mapping 'selected pinned static contract' to the contract parameter and 'immutable public GitHub snapshot' to repository URL and commit SHA. It does not explicitly explain each parameter or enum value, but the schema itself provides the enum and patterns, and the description gives enough context to understand their roles.

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 verifies an immutable public repository by downloading a snapshot and running a static contract. It distinguishes itself from siblings by explicitly requiring a prior eligibility check and by focusing on verification rather than linting or eligibility.

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 instructs to use only after works_public_eligibility returns eligible, establishing a clear prerequisite and ordering with a sibling tool. It also specifies the execution mode (without executing repository commands) and the output behavior (return report verbatim and stop).

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