Recall: Source excerpt

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

Annotations already declare read-only/idempotent/non-destructive, so the safety profile is covered. The description goes further by disclosing output semantics and interpretation rules (owner flag meaning, status vs status_basis) and a strong caveat about never presenting assistant/audit output as an owner decision — genuinely useful context beyond 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?

Purpose is front-loaded in the first sentence, and every later sentence carries distinct semantic content. It is dense and jargon-heavy (user_typed, user_plan_verdict, status_basis) which slightly hurts readability, but nothing is padding.

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 returned record fields (source_id, msg_id, ts, speaker, owner, status/status_basis), which is exactly the gap it should fill. Minor omission of pagination or turn-selection limits, but otherwise complete for a read tool.

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 100%, so the schema already documents all four parameters including defaults. The description only restates the default 3-turns-either-side behavior, adding no syntax or meaning beyond the schema — baseline 3 is correct.

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 first clause names a specific verb (retrieve/recall) and resource (the original conversation around one cited message), which distinguishes it from generic search siblings like recall_search or recall_get. It is clear what the tool returns, though it never explicitly names an alternative sibling to differentiate against.

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?

"check a citation before relying on it" gives an implied trigger for use, which is more than nothing. However, it offers no when-not guidance and does not contrast with recall_get, recall_search or recall_timeline, so the agent must infer the boundary itself.

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