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

Adds context beyond the annotations: it warns about approval and possible credit use, and discloses that writes are never retried automatically — important for a non-idempotent, destructive write. It doesn't say what an attach does to existing photos or what the failure/response shape is.

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?

Four short sentences, front-loaded with the action and the input options, then the prerequisites. 'Needs an API key created by a user' is slightly awkward but earns its place.

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?

Covers the essential preconditions for a nested-parameter write with no output schema: auth requirement, approval flag, size limits, non-retry semantics. Remaining gaps (return value, effect on existing photos) are minor.

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 33%; the description explains the two mutually exclusive image inputs and the confirmed gate, but caption, latitude, longitude, photo_type and the path id parameter get no meaning added in prose.

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 ('Add prospect photo', 'Attach a photo to the prospect's property') and names both accepted sources, making it clearly distinct from the sibling read/delete photo tools.

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 an input-mode hint (base64 for small images, https URL for up to 10 MB) but never says when to prefer this over the sibling upload-url or files endpoints, nor when not to attach a photo. The confirmed=true gate is stated, which is real usage context.

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