guard_evidence

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral information: the two-mode behavior (list vs. full record) and what a full record contains ('digest tail, why, fix'), which tells an agent it can retrieve remediation detail rather than just a count.

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 short sentences, zero filler, and the primary behavior (recent runs) is front-loaded before the id-mode caveat. The parenthetical 'digest tail, why, fix' is terse but each item conveys a distinct payload field.

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 simple (2 optional params, output schema present), so return-value detail need not be spelled out. The one real gap is the undocumented limit parameter; otherwise an agent has enough to call both modes 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 0%, so the description carries the burden. It explains evidence_id well ('one run in full by evidence id'), but says nothing about 'limit' — neither its default of 5 nor what it bounds (run count vs. record size). Half the parameters are therefore undocumented anywhere.

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 names the resource precisely — 'recent verification runs' for the list mode and 'one run in full by evidence id' for the detail mode — so an agent knows exactly what comes back. It does not name any sibling (guard_journal, guard_status, guard_recall are adjacent in scope) to differentiate itself, keeping it short of a 5.

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 second sentence implies the selection rule: pass an id when you need to 'read back' a past failure rather than just count it. That is real but implicit guidance, and there is no explicit statement of when to use guard_journal or guard_status instead, nor any note that both modes are optional (0 required params).

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