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

Annotations already indicate read-only, idempotent, non-destructive behavior, and the description adds substantial behavioral context beyond that: 'Vealth does NOT sell paper offsets,' the retirement lane 'is paused by operator order since 2026-08-04,' and 'this server never takes payment or holds a wallet.' This critically prevents the agent from assuming the tool can execute transactions or quote accurate carbon claims.

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 description is dense and front-loaded with the core purpose ('anchor tool' + estimate + work), but it includes a lengthy digression about Vealth's business model and the paused retirement lane. That context is valuable but not strictly necessary to invoke the tool correctly, so it is slightly less concise than an ideal definition.

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?

Given the tool has no required parameters, a full output schema, and strong annotations, the description covers everything needed: what the estimate means, what it does not mean, what to do next, and the tool's non-transactional nature. An agent has enough context to call it correctly and interpret the result appropriately.

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% — both 'calls' and 'tokens' are fully described with approximate semantics. The description only reiterates that the values are 'rough' and that either can be used, without adding units, ranges, or parameter relationships. Baseline 3 is appropriate because the schema already handles the semantic load.

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 clearly states a specific action: take a rough token or call count and produce an order-of-magnitude CO2e estimate plus provisioning options. It distinguishes itself from siblings by calling itself 'the anchor tool' and explicitly directing the user to 'Call find_work next,' preventing confusion with actual provisioning tools like provision_work or funding_quote.

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?

The description gives clear context on when to use the tool: when you want an orientation-level estimate for an AI session. It also provides a direct next-step routing instruction ('Call find_work next to pick the work') and warns that the estimate is 'orientation only, never a precise carbon claim.' It does not explicitly enumerate when not to use it, but the guidance is sufficient for this simple estimation tool.

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