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

With no annotations, the description carries the full burden and does so richly: any shop member can write, notes are internal and never shown to customers, office audience is restricted to owner/office, worker and payment notes are always office, pinned requires owner/office, and media must already exist on the job. The mention/notification behaviour (email unless opted out, office notes can only mention owner/office, customers never notified) is exactly the kind of side-effect disclosure an agent needs before mutating.

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 core action and target set, then layered with constraints; nearly every clause earns its place. The heavy parenthetical packing makes it denser than ideal and slightly run-on, but no sentence is filler.

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?

Given 10 parameters, no annotations, and an existing output schema (so return values need not be explained), the description covers addressing, permissions, audience, pinning, attachments, and notification side effects. An agent has everything needed to decide and invoke 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?

Schema coverage is only 50%, and the description compensates substantially by explaining target_kind/target_id pairing, job_id/visit_id as shortcuts, audience semantics, pinned privileges, media_ids sourcing, and mention notifications. Only agent_name and body framing are left to the schema, which is minor.

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?

Opens with a specific verb+resource ('Write a note on any shop record') and enumerates the full set of target types, plus the target_kind/target_id addressing scheme. An agent can immediately distinguish this from notes_update or notes_addVoiceMemo 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?

Gives concrete when-to-use context: capture what a worker tells you so the next person sees it, and use job_id/visit_id alone when the note is on a job or visit. It does not explicitly name alternatives such as notes_update for edits or logs_add for timeline entries, so routing vs siblings is inferred rather than stated.

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