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

Annotations (readOnlyHint=false, destructiveHint=false) indicate a write operation that is not destructive. The description adds substantial behavioral context: records are hashed and signed at write time for tamper evidence, returns a specific structure ({ id, content_sha256, signature, recorded_at, verify_url }), requires a Kamy API key with trace:record scope, and consumes monthly Trace quota. There is no contradiction with 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 approximately 7 sentences, each serving a distinct purpose: stating the core function, explaining hashing/signing, providing usage context, noting status options, listing return fields, and specifying auth/quota. There is no redundancy or extraneous information. It is front-loaded with the primary purpose.

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?

Given 11 parameters (2 required) and no output schema, the description covers the return value structure, authentication requirements, and quota consumption. It does not address error handling or rate limits, but it provides sufficient context for an agent to invoke the tool appropriately. The missing output schema is partially compensated by the description of the return object.

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 baseline is 3. The description mentions several parameters (prompt, output, provider, model, tokens, latency) but does not add significant new information beyond what the schema already provides for each parameter. The schema already includes descriptions for tags, feature, status, etc. The description adds no extra parameter-level semantics.

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 clearly states the action ('Record one LLM call') and the specific resource components (prompt, output, provider, model, tokens, latency) into Kamy Trace. It distinguishes itself from sibling tools like trace_search, which searches records, and other tools that handle different tasks (e.g., attest_artifact, record_agent_action). The purpose is specific and 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 provides explicit usage guidance: 'Reach for it when model calls need a reviewable history: regulated workflows, customer-facing generations, anything you may have to explain months later.' It also mentions using 'flagged' status for human review. However, it does not explicitly state when not to use it or compare to alternative tools like record_agent_action, which could record similar events. The context is clear but lacks exclusions.

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