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

The description explicitly calls this a "Durable mutation" that files a ticket, while annotations declare readOnlyHint=true. That is a direct conflict about whether the call writes state, and an agent relying on the annotation would badly misjudge the operation. The otherwise useful details (idempotency, one-read diagnostic cost, no model call) cannot offset a contradiction on the core read/write character of the tool.

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-loads the purpose in the first sentence, then handles report attachment, idempotency, and where answers appear in order of decision importance. Some flavor ("can never arrive naked", "Reports speak public vocabulary") adds tone without adding facts, which keeps it just short of maximally tight.

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 five-parameter write with an output schema, the description covers the decision-relevant unknowns: diagnostic fallback behavior, idempotency semantics, durability, and cost. The one thing it gets wrong is the read/write characterization relative to annotations, which is a correctness problem rather than a coverage gap.

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 baseline is 3; the description still adds meaning by explaining the report_id fallback in cost terms (one read, seconds, no model) and by stating that the same idempotency_key returns the prior ticket regardless of other arguments. It does not add format or length guidance for summary/body, but those are already documented 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 - "Files one durable support ticket for this workspace" - and immediately disambiguates the read sibling by noting answers appear on the ticket in list_support_tickets. An agent can tell what this does and where the result surfaces without opening a 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?

Gives a clear operational rule: attach an existing report_id, or omit it and the cheap workspace diagnostic runs at submit. That is real when/how guidance for the branch the agent must decide. It stops short of naming exclusion cases (e.g., when to prefer the sibling 'submit' tool instead), so it is clear context rather than a full when/when-not map.

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