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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the concrete idempotency mechanic (a reused key returns the existing note rather than repeating the write), which is genuinely useful behavior beyond the hint flag, but says nothing about permissions, rate limits, or what happens to oversized or invalid content.

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 purpose is front-loaded in the first sentence, which is good. However, sentences two and three are near-duplicates — both say that reusing the key returns the first result instead of repeating the action — so one of them is wasted space that could have been spent on the undocumented parameters.

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 mutation with a nested body, three required parameters and no output schema, the description leaves the required cardId identifier unexplained and never mentions base_note_id (presumably for threading), which matters for correct invocation. Annotations cover safety and idempotency, but the entity/card linkage — the most error-prone part of this call — is absent.

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?

Only idempotencyKey carries a schema description (33% coverage), so the description must compensate and only partly does: it explains what entity types a note can target, mapping loosely to body.entity_type. The required params.cardId and body.base_note_id get no explanation at all, and an agent could easily confuse cardId with entity_id in this nested two-object payload.

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 opens with a specific verb and resource ("Adds a note to a company, or to one of its contacts or deals") and its scope is clearly a write of a note, distinguishing it from siblings such as listCompanyNotes, getCompanyNoteCounts and archiveCompanyNotes. Minor imprecision: it says contacts are targeted "by lead ID" while the schema uses a generic entity_id with an account/contact/deal enum, so the terminology is not fully aligned with the payload.

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 tells the agent the three entity types one can attach a note to, which implies usage scope, and gives a rule about reusing the idempotency key only for retries. There is no explicit guidance on when to create a note versus archiveCompanyNotes or how to add a threaded reply, and no prerequisites or alternatives are named.

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