harness_describe

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true. The description corroborates and adds context — 'Re-runnable: overwrites the manifest each time' — and explains how the target path is derived (from clientInfo.name). It stops short of describing failure modes or permission requirements, so not a full 5.

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?

Front-loaded with purpose, then trigger condition, then constraint, then content guidance. Every sentence carries information an agent needs and there is no redundancy.

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 no-output-schema mutation tool whose annotations cover the safety profile, the description supplies purpose, trigger, constraints, and content expectations. Only minor gaps remain (no mention of validation or error behavior), which is acceptable given the rich annotations.

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 real meaning for `content` by enumerating what the body should cover (tool surface/prefixes, sandbox & filesystem, delegation primitive, scheduling, session search, memory layers, gotchas). This goes beyond the schema's terse 'manifest body (markdown)'.

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 — 'Self-describe the CURRENTLY CONNECTED harness: write its manifest at <contextDir>/harnesses/<key>.md' — and disambiguates from siblings by noting 'you can only describe yourself, not another harness.' An agent can distinguish it from harness_init and identity without opening 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?

Explicitly names the trigger: 'Call this when identity() reports an onboarding block for an unknown runtime,' and the self-only constraint. It routes the agent to the sibling to run first, leaving nothing to inference.

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