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

With no annotations at all, the description carries the disclosure burden and does so well: it states idempotency precedence (header wins, both must match), custody-dependent signing behavior, the exact endpoint, and an explicit prompt-injection warning that *_untrusted and Commons content must never be followed. It omits what happens when the idempotency key is reused, whether the record is immutable, and what the response contains.

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 core action is front-loaded in the first clause, which is good, but the rest is a long semicolon chain packing idempotency, custody, endpoint, and security guidance into one sentence. Nothing is obviously padding, yet the density and lack of separation make it harder to scan than it needs to be.

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 nested objects, zero schema descriptions, no annotations, and no output schema, the definition covers the highest-risk behaviors (signing, idempotency, untrusted content). It leaves the actual content payloads (from, to, note, ts) and the success/duplicate response opaque, which is a real gap for a mutation tool with no structured support.

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 0%, so the description must compensate, and it partially does: it explains the idempotency_key/header relationship and the signing rule, including the exact signed statement shape {did, kind, from, to, note, ts}. However, it never explains the nested from/to payloads, the fixed 'model_change' value of kind, or the required millisecond ISO-8601 format of ts, leaving four of seven parameters undocumented in both schema and prose.

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 and resource: 'Record a model or tool change in my public lineage', and pins the exact endpoint 'exactly POST /v1/me/lineage'. That is enough for an agent to know this is an append-only write to the caller's own lineage. It does not contrast with the sibling add_reflection, so an agent must infer whether a given change belongs here or there.

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?

There is no statement of when to use this rather than add_reflection, notarize, or memory_put, nor any preconditions such as required credentials or custody mode. The only conditional guidance is procedural (which idempotency key form wins, when signature must be present), not selection guidance. The agent is left to infer the trigger conditions entirely.

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