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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), but the description adds real value beyond them: it discloses that saving the same key replaces the prior value, that data is opaque to the audit engine and cannot affect Postclick behavior, and that it costs nothing. That resolves the main agent concerns for a mutation tool.

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?

Front-loaded with the free/opaque-payload framing, then the overwrite rule, then the read path. Slightly conversational and longer than strictly necessary, but every sentence carries information (cost, opacity, replacement, retrieval).

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 free-form key/value store with no output schema, the description covers everything needed: what values are accepted, what a subject URI is, what happens on key collision, that the engine ignores it, and how to read it back. Nothing an agent needs in order to call it correctly is missing.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: 'any name, any value', the fact that re-saving a key overwrites it, and that a subject is 'any record' addressed by URI. This clarifies key uniqueness and value freedom beyond the field-level descriptions.

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 (save/attach) and resource (notes on a record), and explicitly distinguishes itself from the sibling `get_notes` by naming it as the read path. An agent can tell it apart from the other audit/page tools 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?

Explains the context in which to use it ('so the work you do around these audits survives between conversations') and names the read alternative `get_notes`. It does not state when NOT to use it, but the intended scenario is clear.

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