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

Beyond the readOnly/idempotent annotations, the description discloses cost and auth ('Free; no account, payment or Gravitate credits'), the processing model ('performs no vision or AI inference'), and explicit non-goals (beauty, age, identity, attraction percentiles, match probability). Those non-goals are the key behavioral fact for an agent deciding whether this tool answers a user's question.

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?

Dense and largely waste-free, with limits and prohibitions collected compactly. Minor weakness: it opens with pricing/credits rather than the purpose, so the key action statement is pushed to the second sentence.

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?

There is no output schema, so the description carries the return-value burden; it says the tool produces totals and applies caps but never describes the response shape (per-observation scores vs. aggregate, ordering). Everything else an agent needs to invoke it correctly is present.

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 67% and already documents the rubric mapping and caps, yet the description still adds unstated constraints: ranks must be explicitly supplied, observations are anonymous and capped at six, no image/URL inputs. It does not clarify the observation_source enum values in prose, leaving part of the parameter space to the schema.

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 object — 'Calculates gravitate-v1 totals and caps for 1–6 anonymous observations' — which no sibling (build_photo_shoot_plan, get_photo_guidance, get_service_status) could be confused with. It also bounds the input scope (1–6 anonymous observations) in the same sentence.

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?

Explicit preconditions are given: 'Use only with explicitly supplied 1–4 ranks ... after reading the methodology' and the hard exclusion 'Never invent ranks from a request without observations.' The negative case ('Accepts no images/URLs') closes the most likely misuse path.

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