Classify Evidence Quality

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds genuinely useful context by naming the classification taxonomy and the numeric grade output, which compensates for the absent output schema. It stops short of explaining the decision logic (how method, evidence keys, or the boolean flags map to a grade).

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?

A single dense sentence with no filler; the action and its output vocabulary are front-loaded. Every clause 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 pure classification function with no output schema, the description usefully discloses the return values (four categories, grade 0-3). However, with four inputs, only 50% schema coverage, and a nested evidence object, it omits how evidence is evaluated and what 'infrastructure keys' mean, leaving the caller unsure how inputs affect the grade.

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 only 50%: method and evidence carry descriptions, but has_issuer_signature and has_principal_binding do not. The description mentions no parameters at all and does not compensate for the gap, leaving the two boolean inputs unexplained beyond their self-evident names.

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 ('classify') and resource ('attestation evidence quality'), and usefully enumerates the four output categories and the grade range (0-3). This clearly separates it from siblings like get_evidence, review_evidence, or is_evidence_fresh, though it never names an alternative explicitly.

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 guidance on when to call this versus related evidence tools (review_evidence, is_evidence_fresh, get_evidence), nor any stated prerequisites or inputs required to get a meaningful result. Usage must be inferred entirely from the name and output taxonomy.

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