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

Adds two traits the annotations cannot express: per-call cost ($0.01, free on failure) and the cross-entity propagation rule (a deal note also surfaces on its company's and contact's timelines). Combined with annotations declaring non-readonly, non-destructive, non-idempotent, the agent has a solid behavioral picture; only a note about whether re-posting duplicates a note is missing.

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?

Two sentences, front-loaded with the action and targets, then the propagation rule and cost. No filler, and the cost caveat is placed where an agent will read it before calling.

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 annotations already covering safety, the description supplies the non-obvious pieces (cost, timeline propagation) and identifies valid targets. It falls short only on parameter-level detail — what `body` vs `title` are for and whether target fields are mutually exclusive — which matters at 0% schema coverage.

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%, so the description must compensate across 6 params. It clarifies the target selectors (contact id or email, deal_id, company_id) but says nothing about the required `body`, the `title`, or whether multiple target ids may be supplied simultaneously — a real ambiguity given four optional target fields and additionalProperties=false.

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+resource (add a note) and enumerates the exact record types it can attach to (contact by id or email, deal, company). That level of target specificity separates it from generic siblings like crm_timeline or hubspot_add_note without needing 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?

Gives content-level guidance ('what was said, decided or learned'), which implies the use case of logging CRM activity. However it never states when to prefer this over hubspot_add_note or when to read crm_timeline instead, and offers no exclusions or prerequisites.

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