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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so safety profile is covered. The description adds genuinely new behavior: a human-approval gate before credit use and the fact that writes are never auto-retried, which tells the agent not to blindly re-issue the call.

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?

Three short sentences with the action front-loaded and the approval/retry constraints immediately after. Minor boilerplate in "before changes or credit use" but nothing that wastes an agent's reading budget.

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 destructive two-parameter delete with no output schema, the description covers the approval workflow and retry semantics. It leaves permanence/irreversibility of the photo deletion and post-delete return state implicit, which the destructiveHint partially absorbs.

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?

Top-level schema coverage is 50%, but every individual property (id, photo_id, confirmed) already has a description and example in the schema, so effective coverage is high. The description only echoes the confirmed=true requirement and does not explain the path identifiers, so it adds little beyond structured data.

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 ("Delete prospect photo"), which cleanly separates it from the file, note, and tag deletion siblings. It does not explicitly name a sibling alternative, but the resource noun is unambiguous enough to route correctly.

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 a precondition ("Requires user approval and confirmed=true") that tells the agent how to call it, but not when to choose it over alternatives such as listing photos first via dealmachine_get_prospects_id_photos or whether there is a soft-delete path. Usage is implied rather than guided.

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