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

Annotations cover the safety profile (non-destructive, idempotent, mutating), but the description adds real behavioral context beyond them: that identical text is not stored as the workspace's own goal, and that changing the goal restarts the clean-send counter that unlocks autonomous sending. These consequences are not derivable from annotations or 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?

Three compact sentences, front-loaded with the core action before the behavioral caveats. The phrasing 'The same text as ours is not kept as the workspace's own' is slightly awkward but earns its place by warning of the no-op case.

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 4-parameter mutation with no output schema and useful annotation coverage, the description supplies strong behavioral and parameter context. It falls short on invocation guidance, and the optional autonomy_threshold and goal parameters lack type/format detail, leaving the definition adequate but not fully rounded.

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 only 50% (job and tommo documented; goal and autonomy_threshold not). The description compensates by explaining the two undocumented parameters: goal as the workspace's own phrasing of the work, and autonomy_threshold as the clean-send count that triggers self-sending. This meaningfully fills the schema gap.

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 gives a specific verb ('Write') and a clearly defined resource ('the workspace's own goal for a job'), and clarifies what a goal represents ('what the work is, in the workspace's words'). It doesn't distinguish itself from the many other save_* siblings, but the resource is unambiguous.

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?

There is no explicit guidance on when to call this tool versus alternatives (e.g., read_a_job or other save_* tools), nor any stated preconditions. The agent must infer the usage context from the semantics of 'goal' alone.

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