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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds context annotations cannot carry: 'The files are deleted' signals permanent, unrecoverable removal, and 'Confirm with the owner which ones first' imposes a confirmation step before invocation. The auth scope ('signed in to Awning') is also stated explicitly.

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 precondition is front-loaded in the first clause, the action follows, and the alternative plus confirmation guidance close it out. Every sentence carries distinct operational information with no repetition of the title.

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 3-parameter destructive mutation with no output schema, the description covers the actor, the precondition, the two target contexts, the identifier source, irreversibility, and the confirmation workflow. Nothing an agent needs to invoke this safely 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 photo_ids, draft_id and business_id are all already documented in the schema with the same provenance hints ('current list of owner_photos', 'from owner_status'). The description reinforces the photo_id source but adds no new format, ordering, or batching guidance (e.g., the 50-item cap) beyond what the schema provides.

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 ('Take photos off the business page') plus the two scopes it operates on (live business page vs. business being set up) and the identifier source ('by photo_id from owner_photos current'). It also explicitly distinguishes itself from the sibling that does the opposite ('to add photos use owner_photos').

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 explicit precondition ('Only for business owners signed in to Awning'), an explicit trigger ('when the owner wants pictures taken down'), an explicit alternative ('to add photos use owner_photos'), and a procedural instruction ('Confirm with the owner which ones first'). No inference is required to pick this tool over owner_photos.

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