remove_publication

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is partly covered. The description still adds genuinely new behavioral facts the annotations cannot express: the cascade across variants, that it cannot be undone, and the response shape (what was removed plus variants_updated).

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 sentences, no waste; the destructive scope is front-loaded, the alternative follows, and the safety warning and return contract close it out. Every sentence 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 destructive 2-parameter tool with no output schema, the description supplies the cascade semantics, irreversibility warning, alternative routing, and a statement of return values — everything an agent needs to invoke it safely and correctly.

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 100% and both parameters (id, profile) are fully documented in the schema, so the baseline is 3. The description mentions `publications` and `variants_updated`, but those belong to sibling tools/the response, not to this tool's own input parameters.

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 (delete) plus resource (publication) and, crucially, the scope: from the profile AND from every variant that lists it. This distinguishes it from sibling mutation tools like save_variant without requiring the caller to open a schema.

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?

Explicitly names the when-not condition and the alternative: to hide it from one CV only, change that variant's `publications` with save_variant instead. It also adds a consent prerequisite ("ask the person first") and the irreversibility constraint.

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