evidence_snapshot

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

No annotations are provided, so the description carries the full behavioral burden. It discloses only that output is 'bounded' and 'raw' (unprocessed), but says nothing about read-only safety, permissions, truncation limits, or cost — thin disclosure for a tool with zero annotation coverage.

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?

It is a single front-loaded sentence with no filler, which is structurally clean. But the brevity is achieved by omission rather than efficiency — key nouns like 'fixed incident category' and 'bounded' are undefined, so terseness here borders on under-specification.

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 return values need not be explained. Yet for a tool with three undocumented parameters and no annotations, the description should supply the missing semantics (what a 'kind' is, what 'bounded' means in practice); it does not.

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 0% across three parameters (kind, path, service), and the description mentions none of them. The critical 'kind' parameter's allowed values or meaning are left entirely undefined, so an agent cannot know what to pass.

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 verb 'Return' and resource 'raw evidence' are identifiable, and 'bounded' plus 'fixed incident category' hint at scope. However, 'fixed incident category' is never defined (the schema's 'kind' parameter presumably encodes it), and nothing distinguishes this from siblings like incident_report or tail_logs, which plausibly return overlapping diagnostic data.

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 statement of when to call this versus incident_report, tail_logs, or propose_remediation, and no prerequisites or conditions are given. 'only for a fixed incident category' hints at a restriction but never tells the agent how to know whether its situation qualifies.

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