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

Annotations already flag destructiveHint=true, but the description goes well beyond them: it names exactly what is destroyed versus preserved ('Existing Space knowledge is preserved and your linked agents aren't affected') and discloses the partial-completion protocol (fence + ordinary cancellation request, has_more/deleted:false semantics). That is precisely the context annotations cannot convey.

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 its blast radius, then the retry rule, then a caveat. Dense and mostly waste-free, though 'Person only.' is cryptic enough to cost clarity rather than add it.

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?

An output schema exists, so return-value explanation is optional (the has_more/deleted references are a bonus). For a destructive single-param tool with annotations, the remaining gap is the identity/sourcing of setup_id and any authorization expectations.

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% for the single required parameter, and the description never explains what setup_id refers to or how to obtain one. The schema supplies only type/format/pattern, so the semantic burden was on the description and it was not met.

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 ('Remove one saved agent setup') plus the cascading effects (fencing hosted continuation, requesting Task cancellation), which cleanly separates it from agent_configure and task_cancel. An agent can tell what this tool does 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?

The retry loop is spelled out explicitly: 'has_more: true means ... call again to finish; that call returns deleted: false.' That is actionable when-to-call guidance. It does not, however, contrast against siblings like task_cancel or agent_configure, and the trailing 'Person only.' is left unexplained.

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