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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real context beyond them: results may be cached up to 15 minutes, reading does not refresh the record, an empty list does not mean the listing is gone, and 'stale' is defined as no push for 12 months. It stops short of describing pagination or response shape, so it is a strong but not exhaustive behavioral disclosure.

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?

The timeline concept and ordering are front-loaded, and the sentences are dense with useful facts, but the empty-list condition is stated twice ('empty when nothing changed since the series began' and 'An empty list means no change since the series began'), which is mild redundancy in an otherwise efficient block.

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?

With no output schema, the description must carry the return-value burden, and it does so reasonably: it lists the possible event types, states the ordering, defines staleness, and explains the empty case. It is nearly complete for a two-parameter read tool, missing only expected shape/volume of the timeline.

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 100%, so both id (from Anuncio.id) and retry_key (retry window, ASCII limit) are already documented in the schema. The description adds no parameter-level meaning beyond reinforcing the 15-minute cache window, 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?

The description names a specific resource (the listing's repository timeline) and a specific payload: the ordered set of change events (abandono, sumiu, renomeado, readme_mudou, manifesto_mudou), newest first. It is clearly distinguishable from siblings like get_listing or listing_status, which return current state rather than history.

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?

Usage is implied (query when you want the change history for a listing) and it notes the listing page exposes the same list as `historico`, but it never states when to prefer this tool over get_listing or listing_status, nor any precondition such as needing an existing Anuncio.id. No explicit alternatives or exclusions are given.

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