save_response_draft

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

Goes well beyond the annotations by disclosing the human-review gate ('Always pending_human_review'), a validation caveat ('Limited validation is not a guarantee of accuracy'), and the absence of send/approve side effects. These are exactly the traits the readOnlyHint=false / destructiveHint=false pair can't convey. It doesn't say what happens on a duplicate ticket_id or how the returned draft is identified.

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?

Four short, front-loaded sentences with no filler; the write action leads and the constraints follow. The phrasing is telegraphic in places ('Limited validation is not a guarantee of accuracy' is slightly ambiguous about what was validated), which costs a point.

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 4-required-param write tool with no output schema, the description covers safety profile, review workflow, and the critical source-quality requirement. Gaps remain around return value (is there a draft ID?) and whether it overwrites a prior draft for the same ticket.

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?

With 0% schema description coverage, the description compensates by explaining that 'sources' must be current policy source IDs (not arbitrary strings, despite the plain string array in the schema) and that customer_text and internal_notes are distinct audiences. ticket_id is left to the pattern constraint in the schema.

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 ('Write a customer reply DRAFT and separate internal notes'), and the emphasis on DRAFT plus 'does not send' clearly separates it from any send/approve action. It doesn't explicitly name the distinguishing sibling (save_kb_draft), so differentiation is inferable 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?

'Requires current policy source IDs' and 'Always pending_human_review' establish the precondition and the lifecycle stage for calling it, and 'Does not send or approve anything' marks the boundary. No explicit when-not or named alternative tool is given, so it stops short of full routing guidance.

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