Get evidence

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

Annotations already declare read-only, idempotent, non-destructive, and closed-world behavior. The description adds meaningful behavioral context beyond those annotations by stating that a text snippet may come from the file or OCR cache and that binaries are never returned.

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 definition is a single compact sentence with the return contents front-loaded and no wasted wording. The parenthetical metadata list and the binaries exclusion are both useful and efficiently placed.

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 read-only retrieval tool with no output schema, the description covers the main returned data and the no-binaries constraint. However, it does not explain the output shape, how grep/lines govern the snippet, or what happens when OCR cache is unavailable.

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 67%, with evidence_id and grep documented but lines lacking a schema description. The description adds context by saying a text snippet is returned, but it does not explicitly explain how lines or grep shape that snippet, so it only partially compensates for the remaining gap.

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 exactly what is returned for an evidence file: metadata fields plus a text snippet, with binaries explicitly excluded. It is specific about the resource and return scope, but does not explicitly distinguish this tool from siblings such as ghost_summary or ghost_describe.

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 implies the tool is for retrieving evidence details, but it gives no explicit when-to-use guidance, exclusions, or alternatives. With several sibling tools available, the agent receives no routing help for choosing ghost_get_evidence over them.

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