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

The description significantly exceeds the basic annotations by disclosing append-only semantics, supersede behavior with old rows retained, target-key refusal based on operator opt-in, and the inability to confirm one's own fact. These details are behavioral and not visible from the annotations or schema.

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?

Every sentence in the description earns its place, delivering purpose, policy, namespace guidance, and procedural caveats in a compact block. The most important behavioral note about append-only semantics 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 write tool with five parameters, no output schema, and only basic annotations, the description covers all actionable aspects: key namespacing, value expectations, evidence, confidence, TTL, target opt-in restrictions, and self-confirmation limits. An agent has enough context to invoke the tool correctly.

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?

Although schema description coverage is 100%, the description adds meaning beyond the schema: key namespacing requirements with examples, evidence being about trust for readers, confidence explicitly not being verification, and ttl_seconds applying to stale facts. This is valuable supplemental param semantics.

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 verb and resource: recording an established fact into shared memory for all future agents. It also distinguishes itself from reading or verifying facts and includes specific policy nuances, making the tool's role unmistakable.

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 context on when to use the tool—after establishing a fact—and detailed when-not constraints: target keys are refused without opt-in, and you cannot confirm your own fact. It does not name sibling tools as alternatives, stopping just short of a fully explicit routing instruction.

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