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

Annotations already declare destructiveHint=true, so the description's 'It cannot be undone' reinforces rather than reveals. However, it goes beyond the annotations by disclosing the response shape ('removed' vs 'skipped') despite there being no output schema, plus the 40-per-call limit — genuinely valuable behavioral context for a destructive operation.

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?

Front-loaded with the action and irreversibility, then usage rules, then result format — a sensible order. It is dense and slightly clause-heavy, and the swap example is verbose, but essentially every sentence carries routing or behavioral information.

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 mutation tool with no output schema, the description covers irreversibility, the exact user-intent conditions, the excluded alternative, the item cap, and the return structure. Missing only explicit permission/authorization requirements, which keeps it short of a 5.

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?

With 100% schema description coverage, the schema already documents kind, items, text, in_item and activity_id thoroughly. The description's 'send exactly the texts the user named, up to 40 per call' maps onto the items array and its maxItems, and adds only the 'only named texts' intent, so baseline 3 is appropriate.

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 states a specific verb and resource — removing the image or audio from named texts — and scopes it with 'leaving the text and everything else as it is.' It actively distinguishes itself from siblings by naming illustrate_items, set_item_images and generate_field_audio, so an agent can route correctly without inspecting schemas.

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?

It gives an explicit trigger ('Call it ONLY when the user asked to remove, delete or take away...'), covers the medium-swap case with a described two-step workflow, and states a hard exclusion ('Never use it to change an image for another image... that is existing: replace in ...'). Alternatives and the condition that selects them are both spelled out.

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