Recall for a task

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses what comes back in full, what is truncated to one line, what is omitted, what happens without a task, and how it behaves if scoring is unavailable. This is unusually explicit about output and failure behavior.

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 description is dense but every sentence earns its place: it explains purpose, invocation, ranking behavior, the no-task mode, and the fallback guarantee. It is front-loaded with the core function and does not waste words.

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?

With no output schema, the description must explain return behavior, and it does so completely: full returns, one-line returns, omissions, no-task listing, and degradation when scoring is unavailable. For a one-parameter recall tool, nothing essential is missing.

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?

Although the schema already documents the 'task' parameter, the description adds crucial semantics: the task should be one sentence, it is optional, and omitting it changes the result entirely to a one-line-per-item listing. This goes well beyond the schema's description.

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 action ('bring forward what earlier sessions recorded') and the resource it operates on, and it is clearly the read-side counterpart to the sibling tool 'record'. It goes beyond the name and title by explaining the scoring behavior, so an agent cannot mistake it for a generic recall tool.

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 gives explicit usage instructions: 'Call it once, at the start of a task, with the task in one sentence' and also explains the no-task variant. It does not explicitly say when not to use it or contrast it with the sibling 'record' tool, so it falls just short of full alternative-route guidance.

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