trmnl_cancel_installation

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

Annotations already declare destructive=true, idempotent=true, openWorld=true, so the safety profile is carried by structured data. The description adds that the target must be a *pending* installation and that it hits DELETE on the remote endpoint, but says nothing about what happens to the installation record, whether it's recoverable, or how a non-pending target is rejected.

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?

The purpose sentence is front-loaded and efficient, but the trailing 'Changes remote state or starts work. Run only within the user-authorized scope.' is generic boilerplate that adds little for a cancel operation.

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?

A destructive, open-world mutation with no output schema and a partially documented schema needs more: the description never covers the outcome of cancellation, error behavior for non-pending installations, or the role of the profile parameter. Annotations cover the safety profile, so the gap is moderate rather than fatal.

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 coverage is only 50% (the nested path.id uuid has no description), so the description is expected to compensate, and it largely does not. The literal 'DELETE /api/plugin_installations/{id}' hints that path.id is the installation identifier, but no format, validity, or profile-selection semantics are added.

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 ('Cancel a pending installation') and pins the scope to pending installations, which separates it from trmnl_complete_installation and trmnl_uninstall_app. It doesn't name those siblings explicitly, so the differentiation is inferred rather than stated.

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 only guidance is a generic authorization caveat ('Run only within the user-authorized scope'), which is boilerplate rather than a when-to-use rule. Nothing tells the agent to prefer this over trmnl_complete_installation or trmnl_uninstall_app, or what condition makes a cancel legal (e.g. installation must still be pending).

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