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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile needs no restatement; the description instead adds genuinely useful behavioral context: the enumerated status values, freshness signalling, quota_exhausted and source_stale outcomes, and the crucial warning that not_covered is NOT proof the deadline stands. However it does not cover paging behavior or rate/quota limits in practical terms, so it is good but not exhaustive.

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 user-facing question, then the return shape, then the status vocabulary, then the sibling routing — a sensible order with no filler sentences. The six-value status enumeration is long but each value carries decision-relevant meaning, so it mostly earns its space.

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?

Output schema exists, yet the non-obvious semantic layer (what each status means, especially that not_covered proves nothing) is explained because it cannot be inferred from the schema alone. Combined with the coverage/enrolment caveat and quota/staleness disclosure, an agent has everything needed to call it and interpret the answer honestly.

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 all three parameters are already documented in the schema, including the exact notice_id format and the cursor's provenance. The description reinforces the "FIRST notice number" trap and gives an example, but that duplicates rather than extends the schema, 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?

Opens with the exact question it answers ("Has the submission deadline of an EU tender moved?") and states the specific return shape: per-LOT previous deadline vs revised deadline, with TED notice references and freshness. It also explicitly positions itself against the sibling search tool ("For searching tenders use ted-eu; this is the change feed").

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 explicit when-to-use (deadline change lookup by first notice number), when-not-to-use (searching tenders goes to ted-eu), the required input form ("Use the tender's FIRST notice number in TED form, e.g. 662865-2026"), and a coverage caveat that most tenders are not watched. That is a full routing decision plus precondition.

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