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

Substantially exceeds the annotations: it discloses credit consumption per depth tier (1/2/10), a shared rate limit of 20 analyses per hour across all Oceanir analysis tools, a depth-2 ceiling for connected apps, and that it returns both the analysis and the case id. It also draws a hard scope boundary (scene only, no faces, no biometrics, no person tracking), which is behavioral context an agent cannot derive from the schema.

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 cost, rate-limit and return information is front-loaded and efficient, but the final third is repetitive: 'never the people in it', 'no face recognition, no biometric identification, no person matching', and 'never who is in it' all restate the same restriction across three sentences. It earns its length on behavior but not on the repeated safety phrasing.

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 4-parameter, non-idempotent, credit-spending tool with no output schema, the description covers everything needed to invoke it responsibly: prerequisites, cost, limits, return values, and scope restrictions. Nothing material is missing.

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, but the description adds meaning the schema lacks: the credit cost framing per depth tier is reinforced, and the connected-app depth-2 restriction is a real constraint on the depth parameter not present in the schema. Case linkage ('existing case') is also clarified contextually.

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 opens with a specific verb and resource: 'Analyze one image and attach the result to an existing case.' The 'attach to an existing case' scope is the key distinguishing trait versus a bare geolocation call. However, it never states plainly how this differs in outcome from the sibling geolocate_image, which it names only to explain credit parity.

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 context is implied rather than stated: the requirement for an existing case points the agent at list_cases/create_case, and the depth-2 cap for connected apps and the 20/hour cap shape when the tool is usable. There is no explicit statement of when to choose this over geolocate_image or verify_location_claim, nor any when-not-to-use guidance.

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