Recall: Has the owner asked this before?

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

Annotations already mark this read-only, idempotent, and non-destructive, and the description adds substantial context on top: the citation fields returned, the exact semantics of the `owner` flag, the meaning of `status`/`status_basis`, and an explicit safety warning not to present assistant, agent_report, or audit records as the owner's decision. That is exactly the kind of interpretation guidance annotations cannot carry.

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?

Front-loaded with the core intent, then builds out citation and status semantics in dense but purposeful sentences. Nothing is clearly wasted, though the owner/status_basis exposition is compressed enough to require careful reading.

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 steps in to explain the return shape (source_id, msg_id, ts, speaker, owner, status, status_basis) and how to interpret it. For a read-only retrieval tool of this nature, an agent has everything needed to call it and to correctly represent results.

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 100%, so the schema already documents limit, project, question, and all_projects, including defaults and range. The description adds no additional parameter syntax or format meaning, so the baseline 3 applies.

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 verb+resource: retrieve earlier questions the owner typed, with their replies and matching decisions. An agent can clearly grasp that this is a semantic lookup over the owner's prior questions. However, it never names or contrasts the close siblings recall_search, recall_decisions, or recall_open_questions, so the boundary between them is left to inference.

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 framing question 'Has the owner asked this before?' implies the usage context (checking prior owner questions). Beyond that there is no explicit when-to-use, when-not-to-use, or alternative routing among the many recall_* siblings. The only usage-like note ('Ask for it explicitly') is attached to a parameter already documented in the schema.

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