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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, yet the description adds two genuinely useful facts: that the schedule and compliance item both survive (i.e. only the link is destroyed) and that compliance:write scope is required. That auth and blast-radius detail goes beyond the structured fields, though it says nothing about response behavior.

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 short sentences, front-loaded with the operation, then the non-obvious survival fact, then the auth requirement. No filler and nothing that could be trimmed without losing meaning.

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 single-parameter link-removal tool with annotations covering the safety profile, the description supplies the two things an agent could get wrong: the object surviving and the required scope. Return values are unnecessary (no output schema), leaving only a minor gap around what the caller should do if the link does not exist.

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?

Only one parameter and schema coverage is 100%, so the schema already documents 'id' and even the resolution path via list_compliance_pm_schedules. The description adds nothing on top of it, which is the correct baseline when the schema carries the load.

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 (unlink) and the exact resource pair (PM schedule from compliance item), which cleanly separates it from delete_pm_schedule and delete_compliance_item in the sibling list. An agent can tell what is being removed without opening the 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?

Usage context is implied rather than stated: it describes the unlink relationship, which signals when this is appropriate over delete_pm_schedule, but never names an alternative or an explicit when-not condition. A pointer to list_compliance_pm_schedules for ID resolution is helpful but is parameter-level guidance.

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