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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false; the description adds genuinely useful context beyond that — the note is publicly visible to the support team and cannot be edited or removed once posted, which is not implied by destructiveHint=false and justifies the mandatory confirmation flow. It does not say what confirm:true returns (a success payload? the created comment ID?) or whether duplicate submissions are possible, so the behavioral picture is strong on consequences but incomplete on outcomes.

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 purpose, then audience, then the mandatory procedure, then the constraint that justifies it. The only mild redundancy is 'always confirm the wording first' restating step (2), which is a deliberate emphasis on a safety-critical action rather than filler.

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 three-parameter write tool with no output schema, this covers purpose, visibility, irreversibility, and the confirmation protocol — everything an agent needs to avoid an unrecoverable mistake. The remaining gap is the response shape of the confirm:false preview and the confirm:true post, which the agent must infer.

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%, so the schema already documents all three parameters; the description still adds meaning by explaining why confirm must be false first (irreversibility) and by specifying that ticketNumber must be copied exactly as returned by list_my_cases, including the leading-zero example. That provenance requirement is a real guardrail rather than a restatement of the schema text.

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 ('Add a note / reply ... to one of their OWN support tickets (Salesforce Cases)') plus the effect ('lands on the case as a public comment the support team can see'). The 'OWN' constraint and the pointer to list_my_cases separate it cleanly from siblings like list_my_cases, close_my_case, and reopen_my_case.

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?

Gives concrete when-to-use triggers in the user's own words ('add a note to my ticket', 'tell them I also tried X', 'update my case'), and prescribes the exact two-step sequence (confirm:false to preview, then confirm:true only after explicit confirmation). It also names the prerequisite source for the ticket number, so the agent knows to call list_my_cases first rather than fabricate an ID.

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