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

Annotations already declare write, open-world, idempotent, non-destructive. The description adds genuinely new behavioral facts: the task is public and cannot be removed (irreversibility), a low daily cap applies per identity (rate limit), and per-task approval is required (auth/consent model). It also corroborates idempotency by prescribing operation_id reuse on retry.

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 action, then adds only constraints that change agent behavior: approval dependency, irreversibility, daily cap, retry rule. Every sentence earns its place; no restatement of the schema.

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 mutation tool with nested params and no output schema, the description covers the approval workflow, irreversibility, rate limiting, and retry semantics. It is slightly silent on what the call returns on success/failure, which would be the remaining useful detail.

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 75%, so structured fields carry most parameter meaning. The description adds semantics the schema omits: operation_id is the key for a safe uncertain retry and the request must be the exact approved payload tied to approved_digest. It does not enumerate the nested request fields, but those are fully typed 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 ('Publish ONE open A2A source-review task') and pins the operation to a named mechanism (SendMessage). It also names the sibling cairn_a2a_preview_task that produces the required input, so the agent can distinguish it from other a2a 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?

Explicit prerequisites and constraints: it must be called 'after the user approved the exact request returned by cairn_a2a_preview_task', and 'each task needs its own approval, so there is no ongoing scope'. The retry condition is also given (reuse the same request and operation_id on uncertainty).

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