Recall: Forgotten ideas

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description still adds meaningful interpretation context: what fields every result carries, what `owner` means, and the rule that only `status_basis: user` reflects the owner's decision. The explicit warning against presenting assistant/audit records as owner decisions is genuinely useful guidance beyond structured data.

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?

Three dense sentences with the result definition front-loaded, followed by citation and status semantics. It is packed with domain jargon but every sentence carries information an agent needs to interpret results. No padding or filler.

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?

No output schema exists, so the description must convey return semantics, and it does: citation fields, `owner` provenance, and `status`/`status_basis` meanings. For an interpretation-heavy recall tool this is near-complete, though a bit more on result ordering/pagination (beyond limit) would seal it.

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 limit, project and all_projects are already documented in the schema, including the 'ask for it explicitly' nuance on all_projects. The description adds nothing about the input parameters; its detail is spent on output fields instead. Baseline 3 is appropriate.

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 pins down a specific, unusual resource set: ideas whose implementation was not_found or unknown and that were not rejected, ordered longest-untouched first. The filter criteria are precise enough that an agent knows exactly what it gets back. It stops short of naming how it differs from related recall tools (e.g. recall_open_questions, recall_decisions), so it is clear but not fully sibling-differentiated.

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 filter definition ('nobody has shown were built', 'not rejected', 'longest-untouched first') implicitly tells the agent when this tool is the right one. There is no explicit when-to-use statement, no exclusions, and no pointer to alternative recall tools for adjacent tasks. Usage is implied rather than stated.

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