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

With only read-only/safety annotations supplied, the description carries the behavioral load and does it well: it discloses that withheld_blocks are reported by kind/reason/section but never text, that revisions outside the clearance return as not_served with a reason, and that older CERT-FR ids answer outside_observation_window rather than not_found. It also notes null semantics for ATT&CK version and observation window when not stated.

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 verb, resource and key, and essentially every clause carries distinct information about the returned payload. It is nonetheless a single very dense block of enumerated fields, which is harder to scan than a short structured list would be.

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?

There is no output schema, yet the description effectively documents the return shape: title, severity, summary, affected products and version ranges, CVE joins, freshness, citation and licence, plus campaign-only sections and the withheld_blocks rule. An agent can predict what it will get and how edge cases surface.

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% and the schema already supplies example ids in four publisher namespaces, so the description adds little; its restatement of 'advisory_id, or _citation.params' duplicates the schema. The provenance hint (id as produced by a search row) is the only marginal addition.

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?

Names a specific verb and resource ('Get one national CERT advisory, CERT-FR threat report or government campaign advisory') and pins the retrieval key ('by its publisher-namespaced id'). It also enumerates the three publisher families handled, which distinguishes it from a generic search.

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?

Explicitly ties id acquisition to the sibling tool ('as a search_national_advisories row gives it (advisory_id, or _citation.params)'), which is genuine routing guidance. It does not state when another tool would be preferable, and the CERT-FR coverage note is behavioral rather than usage guidance.

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