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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds context beyond them: the note surfaces in the task's AI chat and the task is handed to the user for review rather than closed. It does not spell out what happens on a repeated call or what the response contains, but the supplementary workflow context is substantial.

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 core action and its constraint come first, followed by the note-only variant and the sequencing rule, so nothing important is buried. The semicolon-chained second clause is dense but every sentence carries a distinct instruction.

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 mutation tool with no output schema, the description covers the action, its scope, its visible side effect, and the workflow rules an agent must respect. The only gap is what the call returns and how it behaves on repeat invocations, which the idempotentHint only partly covers.

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?

The description maps the two optional parameters to their purpose: result_url as an https link to where the user sees the result, and note as a short account of what was done. It adds meaning beyond the schema by explaining visible effect ('the note shows in the task's AI chat') and by legitimizing a note-only invocation. task_id semantics are left entirely to the schema and its uuid format.

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 opens with a specific verb and resource ('Mark the work on a task handed to an agent as finished') and clearly scopes it to agent-handed tasks ending in 'ready for the user's review'. This distinguishes it from update_task, update_subtask, and start_task_work without the agent needing to open any 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?

It gives explicit when-to-use conditions ('A note alone also fits for asking the user a question or proposing a plan'), a sequencing prerequisite ('Tick the subtasks you did with update_subtask first'), and a hard exclusion with the reason ('Never mark the task itself done: the user does that after reviewing'). The alternative update_subtask is named with the condition that selects it.

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