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

With destructiveHint=true and idempotentHint=true already declared, the description still adds real behavioral detail beyond the annotations: LOCKED facts are revisable, omitting customerName actively clears the stored name, conflicting edits fail rather than overwriting, and identical retries leave history unchanged. The destructive side effect (name clearing) and the concurrency-conflict behavior are disclosed explicitly, which is exactly what the annotations cannot convey.

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 tight sentences, front-loaded with the scope and the kind constraint before the edge cases, and each sentence carries distinct information (LOCKED support, field preservation, name clearing, revision precondition, conflict/retry behavior). Slightly dense but no filler.

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?

An output schema exists and annotations cover the safety profile, so return values and the read/write nature need no restating. The description covers the hazardous and non-obvious behaviors well; the remaining gap is the undocumented status enum and revisionReason/tags semantics for a 9-parameter tool.

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% across 9 parameters, so the description must carry the load; it explains expectedRevision (must come from retrieval), customerName (omit-to-clear semantics), and the title/kind preservation constraint. It leaves status, content, tags, revisionReason, and productId entirely unexplained, so compensation is only partial for a tool this wide.

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 names a specific verb (revise) and resource (an existing metric, customer proof, or discount rule) and enumerates the fact kinds that map to the record_* siblings, so an agent can tell this is the edit path rather than a creation path. It stops short of explicitly naming the alternative tools (record_approved_metric, get_fact_history), so sibling disambiguation is inferred rather than stated.

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 concrete operating conditions: preserve the existing title and kind, pass customerName only when the owner recorded it, and obtain expectedRevision from retrieval. That is clear when-to-use guidance, but there is no explicit when-not or named alternative for cases where revision is the wrong call.

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