deja

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

Annotations only declare openWorldHint=false; the description adds real behavioral context beyond that — that bracketed markers encode the user's own later judgement, that fix should receive output verbatim, and that a successful hit requires an opening acknowledgement line in a specific format. These are non-obvious protocol behaviors an agent could not infer from structured fields.

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 mode list is front-loaded and each line is a single clause that earns its place; the purpose statement comes first. Slightly dense and conversational in the closing sentences, but there is no dead weight.

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 5-parameter, mode-driven tool with no output schema and no siblings, the description covers the mode semantics, the input expectations, and the response acknowledgement convention well. It stops short of describing the general shape of a result beyond the bracketed-marker note, which is the only remaining gap.

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 80%, so the baseline is 3, but the description adds genuine meaning to the `mode` enum by defining what each value actually asks for. It also ties `q` to mode-specific expectations (a path for blame, verbatim output for fix), reinforcing rather than just restating the schema.

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?

Opens with a specific, scoped statement of what the resource is ('This user's own past sessions from every AI coding tool on this machine') and explicitly negates the confusable alternatives ('not general knowledge, not library docs'). The mode list then names seven distinct operations, so an agent knows exactly what each invocation returns without opening the schema.

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?

Every mode carries its own when-to-use condition: blame is 'before you edit or delete it', fix is 'you just hit an error', orient is 'before you go reading'. It also states when *not* to speak ('Say nothing about recalls that did not help'), which is unusually explicit routing guidance.

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