Record a correction from the principal

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

Annotations already declare write semantics (readOnlyHint=false, destructiveHint=false), so the safety profile is covered. The description adds that the record becomes "learning material," implying an append-only store, but says nothing about immutability, whether corrections can be edited later, or how retries behave beyond the schema's request_id note.

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?

Two short sentences, with the triggering condition front-loaded ahead of the storage behavior. Every clause earns its place and no filler is present.

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 seven-parameter write tool with no output schema, the description covers the core intent but omits practical guidance: whether entries are immutable, how to avoid duplicate records (beyond the schema note), and when to prefer a sibling tool such as twin_record_decision. Adequate but with clear gaps.

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 71% and the description touches the key payload fields implicitly via "both versions and the reason." It adds no guidance on workflow, situation, sources, or request_id, so it neither compensates for nor exceeds what the schema already documents. 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?

States a specific verb (capture/record) and resource (a correction from the principal), and clarifies that both the agent's version and the human's decision are stored. It is distinguishable from siblings like twin_record_decision, though it does not explicitly draw that line.

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?

"Call whenever the principal edits, overrides or rejects your work" gives an explicit trigger condition, which is strong usage guidance. What is missing is any exclusion or routing rule versus adjacent tools (twin_record_decision, twin_amend_decision, twin_propose_lesson).

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