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

Beyond the annotations (destructiveHint: true, readOnlyHint: false), the description discloses that the operation cascades to endpoints, permanently removes revision history (making rollback impossible), returns a draft object when staged, and lists specific error triggers. It also notes that edit access is required. This goes well beyond the annotation hint and gives the agent a full picture of side effects.

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 description is dense but every sentence serves a purpose: the first sentence defines the action and modes, the second explains consequences, the third lists errors, and the fourth states the access requirement. It is front-loaded with the core action and does not waste words. Structure is clear and efficient.

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?

Given the complexity of the tool (cascading deletes, two modes, revision history impact, error conditions), the description covers all essential aspects. It explains the draft return value, mentions the inability to roll back, lists errors, and states prerequisites. No critical information is missing for an agent to invoke it correctly, and the lack of an output schema is compensated by describing the draft return.

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?

The input schema already documents all three parameters with descriptions, so the baseline is 3. The description adds meaningful context by explaining how commitMode and draftRevision interact (draft mode requires draftRevision and returns a draft object), and clarifies that lineKey errors occur when missing or unmatched. This adds value beyond the schema, earning a 4.

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?

The description states a specific verb ('delete'), a specific resource ('a line'), and the scope ('every endpoint under it'). It clearly differentiates from siblings like delete_endpoint by scoping to the line level, and it also distinguishes the draft staging mode. The purpose is unambiguous and distinct from similar tools.

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 description explicitly explains when to use draft mode vs. immediate publish mode, and references discard_line_draft as an alternative for undoing a staged delete. It also states the error conditions and access requirement. However, it does not explicitly name delete_endpoint as the alternative for deleting a single endpoint, though the scope makes that clear. Overall, usage guidance is strong but not exhaustive.

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