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

Annotations already cover readOnlyHint/destructiveHint, yet the description adds genuinely new behavior: a four-way taxonomy (settled, thin, contested, superseded) that governs how the returned facts should be weighted, plus the important instruction never to re-propose superseded facts, and a cost signal ('Free'). 'Read-only.' duplicates the annotation, but that is a minor redundancy rather than a contradiction. No output schema exists, so this return-value semantics is doing real work.

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 resource and its key qualifier, then a compact parenthetical defining each status; every clause carries information. The only waste is the fragment 'Read-only.', which repeats the annotation, though 'Free.' earns its place by disclosing cost.

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 one-optional-param read tool with no output schema, the description supplies the critical missing piece — how to interpret the returned facts via the status taxonomy. What it does not cover is residual: the overall shape of the reply and its volume/pagination behavior are neither described nor pinned by a schema.

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% and the single optional `project` parameter is documented thoroughly there, including the name/domain/repo forms and the fallback when resolution fails. The tool description adds no parameter meaning at all, 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?

States a specific resource (remembered facts about this maker) and adds a distinctive qualifier — every fact carries an epistemic status — that separates it from sibling read tools like get_brief or what_nobody_knows. The verb is implicit in the tool name 'recall' rather than spelled out in the description, and it never names a sibling it should be preferred over, which keeps it short of a 5.

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?

Usage is implied rather than stated: it is a retrieval tool, and 'never propose it again' tells the agent how to treat superseded facts downstream. The only explicit guidance is the schema-level note to omit `project` for non-project-specific facts. There is no statement of when to call this versus the other read siblings, nor any prerequisite.

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