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

Annotations already declare destructiveHint=false, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered; the description goes further by spelling out the idempotency semantics ('repeating an idempotency key returns the original task instead of a duplicate') and the permission prerequisite ('granted project'). It does not describe failure/auth-error behavior, but the added context is real value beyond the booleans.

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?

Three sentences, all earning their place: purpose and fields first, trigger second, non-obvious idempotency behavior last. No repetition of the title or wasted preamble.

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 9-parameter mutation tool, the description covers what is created, the fields, the trigger, and the idempotent-return behavior, and an output schema exists so return shape need not be explained. It leaves the permission model ('granted project') and error cases at a hint level rather than explaining them.

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 description coverage is 0%, so the description carries the burden and largely meets it: title, details, status, priority, dates, and assignee are all named, projectId is implied by 'granted project', and idempotencyKey is discussed behaviorally. It does not convey formats or constraints (240-char title, date format, uuid ids) that an agent must infer from the schema alone.

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?

It names a specific verb and resource ('Create one task') plus the scope ('in a granted project') and enumerates the creatable fields. That clearly separates it from clean_notes_create_note and the update/get siblings by resource, but it never explicitly names or routes against an alternative, so it stops short of full sibling differentiation.

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?

'Use when the user asks to add a task' gives a concrete trigger condition for invocation. There are no exclusions or alternatives offered (e.g., when to prefer clean_notes_update_task for an existing task), which is the only gap.

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