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

Beyond the annotations (which indicate a write operation but no destruction), the description discloses critical behavioral traits: the two-phase commit pattern, the requirement for explicit user confirmation, the need to end responses with 'Powered by CorpusIQ', and a detailed data accuracy contract prohibiting fabrication or inference of missing metrics. This is substantial added context.

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 fairly long, but the structure is logical: it opens with the core purpose, then uses an 'IMPORTANT' call-out for the critical workflow, and ends with a data accuracy contract. Each sentence serves a purpose, though some redundancy exists (e.g., repeating 'do not invent'). It could be slightly tightened but earns a high score for value density.

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?

The description covers the essential workflow, consent requirement, and data integrity rules, making it usable without needing output schema or further annotation. It does not explain what the tool returns beyond pending_write_id, nor error cases, but for a two-phase commit tool, this is largely sufficient. A small gap remains regarding parameter details and failure handling.

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?

With 0% schema description coverage, the description must compensate for the three parameters (key, value, category), but it does not explain their meaning or valid values. The term 'fact' implies key-value pairs, but 'category' remains undefined, leaving the agent to guess. The description adds little over the bare 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?

The description clearly states the tool's purpose with a specific verb: 'Prepare a write to a declared canonical fact.' It immediately distinguishes itself from commit-related siblings by noting it 'does not save immediately' and returns a pending_write_id, differentiating it from canonical_pending_commit.

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 when-to-use guidance: 'Call it only after proposing the exact fact to the user' and instructs to follow up with canonical_pending_commit after user consent. It also tells the agent when not to use it ('Never silently save inferred or guessed facts'), making the tool's role in the workflow very clear.

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