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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the baseline is low. The description adds two genuine behavioral points beyond them: results may be partial ("any available excerpt") and a negative result is not proof of non-existence in the official source. It omits what happens on an ambiguous identifier (error vs. candidate list), which matters for a lookup keyed on a single string.

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 clauses, front-loaded with what is retrieved and the accepted identifier forms, then the return shape, then the caveat. No filler, no restatement of the title.

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, non-destructive lookup with no output schema, the description covers purpose, identifier forms, approximate return content, and the negative-result caveat. The remaining gap is whether an ambiguous match raises an error or returns multiple candidates, which the "requires refinement" phrasing leaves ambiguous.

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% and the single parameter is documented only as "Identifier", so the description carries the whole burden here. It rises to the occasion by specifying the two accepted identifier namespaces, which is exactly the disambiguation an agent needs to build a valid call, though it supplies no example value or format shape.

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 gives a specific verb and resource ("Retrieve a specific tax administrative document") and names the two supported identifier schemes (DGT:consultation-number, DYCTEA:registry), which is unusually concrete. It implicitly separates itself from read_administrative_document by scoping the return to "identity, metadata and any available excerpt", but it never names that sibling explicitly, so the differentiation is inferential rather than stated.

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?

There is a useful usage rule for the ambiguous case ("Ambiguous references require refinement"), which tells the agent what to do when the identifier is imprecise. However, nothing says when to choose this tool over search_administrative_documents (unknown reference) or read_administrative_document (full text), which are both plausible alternatives on the sibling list.

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