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

Annotations only say destructiveHint=true; the description goes well beyond that by disclosing reversibility (the prior revision still contains the endpoint and can be restored), the exact return shapes per mode ({draft} vs {deleted: true, endpointId}), an error taxonomy distinguishing validation errors from retryable publish failures, and the edit-access requirement.

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 mode choice, and every clause earns its place (reversibility, return shapes, error taxonomy). It is delivered as one very dense block of prose with no breaks, which slightly hurts scanability but not information density.

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?

With no output schema, the description compensates by stating both return shapes, all failure classes, the auth prerequisite, and the rollback path. An agent has everything needed to call it correctly and to recover from a mistake.

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 100% and the schema itself already documents lineKey, endpointId, commitMode defaults, and the draftRevision requirement, so the baseline is 3. The description still adds value by coupling the commitMode/draftRevision parameters to observable behavior (draft returns {draft} instead of deleting), which is semantic information the schema does not carry.

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?

Specific verb + resource ("Delete an endpoint and its targets") with the two execution modes named up front. It is clearly distinguishable from siblings like discard_draft_endpoint, update_endpoint, or delete_line without opening any 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 states when to use draft mode (commitMode "draft" with draftRevision) versus immediate publish, and routes recovery through named siblings: list_config_revisions to find the prior revision and rollback_config to republish over the deletion. Conditions that select each path are spelled out, not implied.

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