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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is lighter. It adds real value by disclosing the return shape { valid, issues } in the absence of an output schema, plus the pre-store gate. It doesn't say whether validation is strict or advisory, or what issues contains, so not a 5.

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?

Two sentences, no filler: the first defines what is checked, the second gives the return shape and the call-site guidance. Front-loaded and appropriately sized for a single-parameter tool.

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-parameter validator with no output schema, the description covers what is checked, when to call it, and the top-level return keys. It leaves the contents of `issues` unspecified, which is a minor gap given there is no output schema to fall back on.

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 3 is the baseline, but the schema's fact object is free-form (additionalProperties: {}), meaning the description's enumeration of expected fields is what actually tells the agent what to put in. It adds specifics like the dotted predicate format and citation-bearing provenance beyond the schema's terse list.

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 verb and resource ("Check that a fact conforms to the FactLot model") and enumerates the model's parts: subject ID, dotted predicate, as_of date, provenance with citations, optional AI-use rights. No sibling tool does validation, so no differentiation is needed and none is missing.

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?

Gives an explicit trigger: "Call before storing or sharing extracted facts." That is a clear when-to-use. It does not name an alternative or state when not to bother (e.g. already-validated facts), so it stops short of a 5.

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