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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety bar is lower, but the description adds real value by disclosing the cascade effect: the rows the link filled are removed along with it. That is the single most consequential behavioral fact for this tool and it is not in the schema or annotations. It does not cover permissions or error behavior when the link is absent.

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 short sentences with the destructive consequence front-loaded rather than buried. Minor deduction for the pronoun-heavy phrasing 'The rows it filled go with it', which takes a moment to resolve but does not bloat the description.

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 three-parameter destructive tool with no output schema, the description covers what is removed and where the inputs come from, which is the core need. It is silent on whether the removal is reversible, what happens if the link no longer exists, and what the call returns, leaving gaps an agent calling a destructive endpoint would reasonably want filled.

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 the enum on kind is documented, so the schema carries the parameter work. The description only adds provenance ('kind + feedId from list_apps'), which is useful but marginal and duplicates hints already present in the schema property descriptions.

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 phrase and resource: 'Stop reading a calendar link', with a parenthetical naming the identifying inputs. Combined with 'The rows it filled go with it', an agent can tell this deletes a calendar feed link rather than a site or page, and it is clearly the inverse of the sibling share_calendar_link. The only softness is that 'stop reading' is a euphemism for removal rather than a direct verb.

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?

Usage is implied rather than stated: the reference to list_apps tells the agent where to obtain kind and feedId, and the pairing with share_calendar_link suggests this is the undo path. There is no explicit 'use this when…' clause and no mention of when not to use it (e.g. when only the imported rows should be cleared).

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