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

Annotations already mark idempotentHint=true and readOnlyHint=false, but the description goes well beyond them. It discloses that the actor is stamped from the credential, never the body; that on CYCLE tasks text can become executor prompt or reviewer input; and that idempotency_key makes a replay return the same message. It also states side-effect behavior like releasing a blocked asker.

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?

The description is dense but every clause earns its place. Core purpose is front-loaded, followed by exclusions, permission tiers, special-case behaviors, and constraints, with no filler or repetition 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 7-parameter write tool with no output schema, the description is remarkably complete: it covers protocol, permissions, exclusions, special routing, idempotency, length limits, and behavior on CYCLE tasks. An agent can determine whether to call this tool and which parameter values are valid without needing external context.

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 baseline is 3, but the description adds substantial meaning: body length cap, the meaning of answer in the dispatcher vs human case, the replay behavior of idempotency_key, and the CYCLE-task prompt implications. It also clarifies that no actor parameter is needed because identity comes from the credential.

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?

The description states a specific verb and resource, 'Post a message on a task trail,' and immediately narrows the protocol and kinds: 'protocol v0.2 trail_messages: kind question, answer, handoff or discussion.' It also differentiates itself from task-completion actions by declaring that a message 'never completes a task, never satisfies a gate and never pages anyone.'

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 description explicitly specifies when this tool is appropriate and when it is not: ordinary tasks are 'write tier,' CYCLE tasks require agent:dispatch, human-addressed questions return 403, and finding/decision kinds 'cannot be posted.' It also states the effect of kind=answer on dispatcher-addressed question tasks, giving an agent clear routing context without needing another tool description.

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