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

Annotations cover the safety profile (not read-only, not destructive), and the description adds real behavior beyond them: dedupe semantics ('if an active fact with the same text already exists it is returned instead of duplicated (created: false)'), the default category, and an explicit non-effect ('does not regenerate the creator memory'). The only tension is that this dedupe behavior reads as idempotent while the annotations set idempotentHint=false, which is a minor inconsistency rather than a misleading claim.

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?

Three short sentences, front-loaded with the core action, then defaults, then dedupe behavior, then the boundary note. No filler and every clause carries information an agent would otherwise have to guess.

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 3-param mutation with no output schema and no schema descriptions, the description should say more about the return shape (only 'created: false' is disclosed) and about brandId/targeting. Safety and dedupe behavior are covered, so it is adequate but leaves clear gaps.

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 3 params, and the description compensates only partially: it explains what 'fact' is and that 'category' defaults to 'preferencia', but never lists the enum values or says what 'brandId' scopes the fact to. Baseline 3 for a partially-compensated low-coverage schema.

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?

States a specific verb and resource ('Record a fact about the creator in the learning ledger') plus the implied source (manual) and status (active). The closing line 'Does not regenerate the creator memory' explicitly separates it from update_creator_memory/regenerate_creator_memory, so an agent can distinguish it from the many sibling *creator_fact and *creator_memory tools without opening a 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?

Usage is only implied: the dedupe rule and the 'does not regenerate the creator memory' note tell the agent this is a single-fact append rather than a memory rebuild, but there is no explicit statement of when to prefer this over add_restriction, review_creator_fact, or update_creator_context, and no exclusions.

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