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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so 'Read only' largely restates structured data. The real added value is disclosing return-field semantics, notably 'via (portal, link or autopilot; null while open)', which is behavior the agent could not otherwise know — but the description stops short of explaining what status/result values look like.

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?

Two dense sentences, front-loaded with what is returned and terminated by a scope constraint. The parenthetical about 'via' is compact and informative rather than wasteful; nothing needs trimming.

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-record getter with one fully documented parameter and no output schema, enumerating the returned fields and the null-while-open case is close to sufficient. Minor gaps remain: no description of the status/result value space and no note on what happens for an unknown or malformed change_id.

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 itself explains that change_id is 'as returned by propose_ad_change, propose_post or list_changes'. The description adds no additional syntax, format, or error-condition detail beyond that, 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?

Clear specific verb-resource pair: retrieves 'one proposed or decided change' and enumerates the fields it carries (before, after, reason, status, result, via). The singular 'One' implicitly contrasts with list_changes but never names it, so sibling differentiation relies on inference.

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 only implied by 'One ... change' plus the required change_id. It does provide a genuine exclusion — 'approval happens in Vibeking' tells the agent not to look for an approve action here — but it never states the natural complement, e.g. use list_changes to browse or propose_ad_change to create one.

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