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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real value beyond them: the draft-visibility privacy rule and the exclusion of scoped specialists, which an agent could not infer from structured fields.

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?

Three dense sentences with no filler and the scope/ownership rule front-loaded. The first sentence is slightly overloaded with the field list, but nothing is wasted.

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?

No output schema exists, and the description compensates by naming the returned fields and the privacy semantics of drafts. Combined with complete parameter documentation, an agent has enough to invoke it correctly, though pagination/ordering behavior is not stated.

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 baseline is 3; the description reinforces the drafts enum semantics ('only pending drafts written by the connected user') and enumerates the returned fields (category, timestamps, status, owner labels, confidence, provenance), adding meaning beyond the schema for a tool with no output schema.

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 (Recall) and resource (recorded X1 decision memory) plus the scope (own record or assigned client) and the dimensions available. An agent can distinguish this from get_client_profile or get_client_activity without opening schemas.

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 ownership rule (own record vs assigned client, professionals must pass clientId) and gives explicit conditional guidance for the drafts mode. It also states exclusions ('every other professional draft remains private', 'Scoped specialists are excluded'), but never names a sibling as an alternative.

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