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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the read-only nature is clear. The description adds valuable context about the `partial` flag indicating headroom is an upper bound, and explains the meaning of `reason: foreign_registrar_pricing` for unknown costs. It also clarifies that transfer prices are not renewal prices. This goes beyond the annotations, though it does not describe the exact output structure (no output schema), but that is partially covered by describing the fields.

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 moderately long but every sentence serves a purpose, covering usage context, output specifics, and caveats. It is front-loaded with 'Use this before recommending anything with a price', which immediately tells the agent when to invoke. No filler or repetition.

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's complexity (multiple financial concepts, partial data, unknown costs), the description covers the essential caveats: headroom upper bound when partial, unknown cost reasoning, and transfer price distinction. The single parameter is clear, and the output schema is absent, so the description's field listing helps the agent understand what to expect. It is complete enough to avoid misinterpretation.

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 has only one parameter, `project_id`, with no description. The parameter is self-explanatory, so the description adds minimal value by not detailing what project_id references if ambiguous. However, since there is only one required parameter and it is standard, the agent can infer meaning. The description itself does not elaborate on the parameter, but the schema coverage is 0%, so the description does not need to compensate for missing param descriptions; the baseline is 3 because the single param is trivially named.

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 the tool's purpose: to retrieve the fiduciary readout for a project, including budget, costs, headroom, and unknown counts. It specifies the verb 'get' and the resource 'finance', and the context 'Use this before recommending anything with a price' distinguishes it from siblings like `quote_domain` or `get_draft`.

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 explicitly instructs when to use the tool: before recommending anything with a price. It also tells the agent to read `carry_unknown_count` before quoting headroom, and warns against treating transfer prices as renewal prices. It implicitly differentiates from `quote_domain` by focusing on account-level finances rather than per-domain quotes.

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