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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description adds real context on top: what is and is not mutated, that the endpoint carries a key so key changes happen elsewhere, the permission required, and the guarantee that no provider key is taken or returned. It never contradicts the annotations, and the 'only the name changes' line actively reinforces destructiveHint=false.

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 purpose, then scope, then alternatives, then the id source and permission — a sound information order with no filler. The parenthetical 'because it carries a key' is slightly compressed reasoning that takes a moment to parse, but every sentence still carries actionable content.

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 two-parameter mutation with no output schema, the definition covers everything an agent needs: what changes, what does not, the permission gate, where the id comes from, and the guarantee that no secret is transmitted. No return-value explanation is needed since the tool is a no-output rename and the description says so implicitly via 'never takes or returns a provider key'.

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%, so the baseline is 3, and the description goes beyond it by stating where `endpoint_id` originates (`list_ai_endpoints`) and by scoping what `name` affects (the label only, not the address or key). It stops short of any naming constraints or length/format rules, so it is an improvement over the schema rather than a full substitute.

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 ('Rename one of the organisation's OpenAI-compatible AI endpoints') and immediately bounds the scope to the name only, explicitly noting that address and stored key are untouched. That scope statement distinguishes it from `update_ai_environment`/`ankra ai endpoints update` work without the agent needing to open sibling schemas.

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 (rename only), when-not-to-use with named alternatives ('changing either is a portal or `ankra ai endpoints update` lane'), and the precondition ('Needs ai.manage (organisation owners and admins)'). It also routes the agent to `list_ai_endpoints` to obtain the id, which is the only upstream step required.

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