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

Annotations already declare the safety profile (not read-only, not destructive, not idempotent, closed-world), so the description's main added value is disclosing that the change is expressed in free-form natural language and that the tool returns an updated preview rather than only an acknowledgement. It does not say what happens when the request is ambiguous or unsupported, which is the one behavioral gap.

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?

One front-loaded sentence plus a return-value clause; nothing is padding. The four examples are slightly more than strictly necessary, but each illustrates a different kind of edit (time, color, field text, design), so they earn their place.

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 natural-language mutation tool this covers the essentials — what to send and what comes back — and no output schema exists, so the mention of an updated preview is the right level of detail. It still omits error behavior, whether changes are applied cumulatively to the draft, and whether the preview must be committed separately.

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 0%, so the description carries the full burden for two parameters. It compensates well for the opaque "request" string by supplying four worked examples of the expected plain-language phrasing, which is the single most important semantic detail; draft_id is left to the name alone but is self-describing and constrained to an existing draft.

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?

"Change a draft" is a specific verb+resource pair, and the four quoted examples make the transformation (time, colors, text fields, design) concrete. It does not name a sibling such as make_invitation or get_invitation, so the boundary with siblings is inferred from the name 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 required draft_id and the word "draft" imply this edits an existing invitation rather than creating one, and the examples imply follow-up refinement. But there is no explicit "use this when..." statement, no mention of when to use make_invitation or get_invitation instead, and no prerequisites or ordering guidance.

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