palinode_corrections

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds material beyond that: candidates are proposals 'awaiting review, never applied,' and the tool cannot trigger detection. Those are non-obvious operational facts an agent could otherwise assume incorrectly.

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 front-loaded sentences: what it lists, what a candidate contains, and the advisory/preconditions. Dense but every clause carries information; only the final clause about the CLI/REST detection pass is slightly beyond the minimal core, and it is still useful routing context.

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?

With no output schema, the description compensates by describing the return shape: each candidate quotes a bounded span of the user's own words plus session, turn and project. Combined with the emptiness precondition and advisory status, an agent has everything needed to call and interpret it.

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 100% with only two optional filters (project, since_days), and the schema documents each including the 'omit for all' default. The description adds no syntax or format detail beyond what the schema already provides, so the baseline 3 applies.

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?

Specific verb+resource: 'List correction candidates mined from harness session transcripts,' with a concrete enumeration of what qualifies (overturned decisions, rejected approaches, remember requests). This clearly distinguishes it from siblings such as palinode_correction_apply or palinode_correction_preview, which act on candidates rather than listing them.

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?

Gives real context for when the tool yields data: 'the list is empty unless the store's operator enabled transcript capture and named the transcript paths in config,' and notes that a fresh detection pass is deliberately an operator action on the CLI or REST API, not this tool. It stops short of naming a sibling tool to use instead, but the precondition and exclusion are explicit.

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