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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false). The description adds substantive behavior the annotations cannot convey: the write is a PRIVATE draft that never publishes, it requires owner approval through a MyLegend link, and the revision value is an optimistic-concurrency guard against clobbering existing drafts.

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?

Five short sentences, each earning its place: gating condition, field-scoping rule, revision procedure, privacy/approval outcome, and caution against fabrication. The most important constraint (owner-initiated, draft-only) is front-loaded.

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 non-destructive, non-open-world mutation with no output schema, the description covers the essential context: who may trigger it, what subset of data to send, the revision protocol, and that the result is a private draft requiring external approval. The one remaining gap is that it does not say what the tool returns after a save (new revision, draft id), which the absence of an output schema leaves to inference.

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% and the fields object has eight nested properties that carry no descriptions anywhere. The description compensates for expectedRevision by explaining the read-then-submit revision protocol and the 0 sentinel, and constrains fields to an explicit user-chosen subset, but it does not clarify the individual profile fields (headline vs publicIntroduction, roles vs expertise).

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 ('Save ... their MyLegend agent') and immediately scopes it as a draft operation that never publishes, which cleanly separates it from the read counterpart get_my_agent_draft and from any publish path. An agent can identify the operation without opening the schema.

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?

It gives an explicit precondition ('only when the signed-in owner explicitly asks to create or edit'), an explicit constraint on input scope ('only the fields they choose to share from this conversation, never the whole chat'), and names the prerequisite step (read the current revision first, 0 if no draft). It also states the forbidden behavior (do not invent credentials or infer sensitive details).

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