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

Annotations already flag destructive, non-idempotent, open-world behavior, and the description adds real behavioral context beyond them: revision prevents overwrite, a completed dependency emits a resume suggestion rather than auto-completing the task, and private calls need provider opt-in. The connection credential's handling is only covered in the schema.

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?

Four dense sentences, each carrying a distinct fact (purpose, concurrency, side effect, privacy) with the core purpose front-loaded. Slightly terse and jargon-heavy ('host work', 'resume suggestion') but no filler.

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 no output schema and strong annotations, the description covers purpose, concurrency semantics, side effects, and a privacy prerequisite. It omits any mention of the connection credential requirement, though the schema documents that fully.

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?

At 78% schema coverage the baseline is near 3, and the description pushes above it by explaining the role of task_id + revision (overwrite prevention) and dependency_request_id (resume suggestion emission). It leaves scope, status, channel_id, and authorization to 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 — 'Save an explicit private local goal or blocker' — and the qualifier 'local' plus 'Tincan cannot see host work' makes the scope distinct from sibling task/edit tools. It stops short of naming a sibling like a2a_task_update or task_context_list to fully disambiguate.

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 implies when to use it (recording a goal/blocker that the host cannot observe) and adds a prerequisite ('Provider processing requires private opt-in'), but it never states when NOT to use it or which sibling to pick instead (e.g., task_context_list vs a2a_task_update).

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