evidence_inspect

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context beyond that by specifying the output structure: it includes the evidence record fields and a live re-check with enumerated statuses (same, moved, changed, gone, ambiguous). This informs the agent about the dynamic verification behavior that annotations cannot convey. No contradictions with annotations.

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

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

The description is a single sentence that front-loads the core purpose ('One evidence record') and then enumerates components. It is dense but not bloated; every element adds value (fields, verifiability, citing claims, re-check statuses). The enumeration is clear and the 'Read-only' note is redundant but minimal. It loses a point only for being slightly overloaded with details in one breath.

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 simplicity (one parameter, no output schema), the description is sufficiently complete. It explains what the tool returns (including the re-check status), which is the key information an agent needs to invoke it correctly. It does not mention error behavior (e.g., missing evidence_id) or expected input validation, but those are minor given the clear param description and annotations. The absence of an output schema raises the burden slightly, but the description covers the essential result shape.

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 covers the single parameter (evidence_id) fully, including format and provenance ('from claim_inspect'). With 100% schema coverage, the description adds no additional parameter-level detail. It does not specify constraints like regex or required format beyond the example, so it meets the baseline of 3 but does not exceed it.

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

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

The description states a specific verb ('inspect') and resource ('evidence record'), and enumerates exactly what is returned: type, locator, commit, hash, excerpt, verifiability, citing claims, and a live re-check status. This clearly distinguishes it from sibling tools like claim_inspect or node_inspect, which target different object types. The inclusion of the re-check concept is unique and further sets it apart.

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

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

The description does not explicitly state when to use this tool versus alternatives. It implies usage when you have an evidence_id (from claim_inspect), but it does not provide explicit conditions or exclusions (e.g., 'use claim_inspect for claims, evidence_inspect for evidence'). The param schema points to the source of the ID, but the description itself lacks direct usage guidance.

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