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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's job is to add consequence detail — and it does, in a way annotations cannot: the image stops loading in already-sent emails, not just future ones. That is exactly the retroactive effect an agent needs before calling. The only gap is repeat-call behavior, which the annotations flag as non-idempotent without the description explaining what a second call returns.

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?

Two sentences, zero filler, with the destructive consequence front-loaded before the caution. Every clause 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?

For a one-parameter destructive tool with no output schema, the definition covers the irreversible effect and the pre-check, which is the critical content. The missing piece is sourcing and formatting the image_id, the one thing an agent must supply correctly to invoke it.

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 description coverage is 0% and the single parameter image_id is never mentioned in the description, so there is no hint on where the identifier comes from (e.g. list_images) or what format it takes. With one undocumented param, the description carries the burden and does not compensate.

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 a hosted image') and immediately qualifies scope with the blast radius ('stops loading in every email that uses it, sent ones included'). This clearly separates it from upload_image and list_images, and no agent could confuse it with the delete_* siblings for other resources.

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 a concrete precondition — 'check it is unused first' — which is actionable guidance for a destructive operation. It stops short of naming the verification path (e.g. list_images or a usage lookup) as an explicit alternative, so it is clear context without a full when/when-not routing.

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