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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation risk is known. The description adds valuable behavioral context beyond annotations: the write-tier approval flow (manager approval, from-now-on vs just-once), the re-injection behavior at next voice mint, and the constraint that faith content stays operator-authored. It doesn't fully detail what 'settleable' means or the exact re-injection mechanics, but it adds substantial context beyond the annotations.

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?

The description is well-structured with the core purpose and usage in the first sentence, followed by content guidance, then the approval flow. It's slightly dense with the bracketed write-tier section, but every sentence earns its place. The front-loading of the primary purpose and the clear separation of the approval caveat make it easy to parse.

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 write tool with no output schema, the description covers the key operational details: when to use, what to write, length limits, approval flow, and re-injection behavior. It doesn't explain the return value or error cases, but the absence of an output schema lowers that burden. The main gap is not fully defining 'settleable' or the exact mechanics of 'open + settled_keep', but these are domain-specific terms that may be understood from context.

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%, so the schema already documents all three parameters. The description adds context for the 'lesson' parameter by specifying content guidance ('what worked, what failed, which principle') and length constraint ('Short notes only'), which complements the schema's example. However, it doesn't add meaning for 'source' or 'companyId' beyond what the schema provides. Baseline 3 is appropriate since the schema does the heavy lifting.

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 states a specific verb ('Append'), a specific resource ('one settleable CoS lesson'), and a clear scope ('for THIS operator only'). It also distinguishes itself from the sibling append_cos_preference by specifying the self-improve construction context and the 'settleable' qualifier. The purpose 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?

The description explicitly says when to use it ('Use after a clear win/miss on a call'), what content to include ('what worked, what failed, which principle'), and what not to include ('Short notes only — not transcripts'). It also provides explicit behavioral guidance about approvals and when to call it ('Call it on the first clear ask; the card is the yes — do not re-ask in chat'). This is exemplary usage guidance.

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