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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the bar is lower. The description still adds real behavioral context beyond them: duplicate ids resolve to a canonical record, and jurisdiction coverage varies. The occupancy-vs-completion distinction is a meaningful semantic warning an agent could not derive from structured fields. It omits what happens on an unknown or out-of-coverage id.

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 short sentences, front-loaded with the verb, resource and key, with the caveat placed last. Little waste, though 'Coverage varies' is left unqualified and reads as an afterthought rather than a usable constraint.

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 single-parameter read tool with no output schema and full annotation coverage, the description supplies what matters: the identifier type, the returned fields, dedup behavior, and a caveat about certificate interpretation. Only error/not-found behavior for a bad UUID is missing, which is a minor gap.

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 0% for the single certificate_id parameter, but the schema itself declares type string with format uuid, so the description's 'by UUID' is largely redundant. The genuinely additive point is that a duplicate id resolves to a canonical record, which tells the agent how id collisions are handled. That is thin compensation for a parameter with no description in the schema.

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 ('Get an occupancy or completion certificate') and scopes it to 'by UUID', which implicitly separates it from the search_* siblings. It also names the two returned fields (certificate_status, co_date_basis), so an agent knows what it will receive. It stops short of explicitly naming search_certificates as the alternative for non-ID lookups.

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 'by UUID' phrasing implies this is a direct-lookup tool rather than a search, and 'Coverage varies; a completion certificate does not establish occupancy' warns the agent not to over-read results. However, there is no explicit when-to-use/when-not statement or reference to search_certificates for discovery, so usage must be inferred.

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