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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description goes meaningfully beyond that by disclosing gating logic: clients that have not accepted the advisor disclosure are only counted as 'withheld', and match cards are masked 'as the client sees them' once vendors are notified. Those are non-obvious behavioral facts an agent could not infer from annotations or an empty schema.

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?

It is a single ~100-word sentence that opens with a long subordinate eligibility clause ('For a signed-in administrator of a consultant or private equity firm whose PreShiftIQ account has an authenticator app turned on') rather than the tool's purpose. The content is dense but every clause carries information; the failure is structural, not verbosity. Splitting into eligibility / returns / edge-case sentences would make it far easier to parse.

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?

An output schema exists and a zero-parameter tool is low complexity, so the description did not need to enumerate return fields, yet it does, which is partly redundant but harmless. The one genuine gap is that the withheld-client behavior is described as a count without saying where that count appears in the response. Otherwise an agent has everything needed to decide to call it and interpret the result.

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?

The tool takes zero parameters, so there is no parameter semantics to add and the baseline of 4 applies. The description correctly adds no parameter discussion, instead spending its length on scoping conditions that substitute for filters an agent might otherwise expect.

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 names a specific resource (the assessments of clients the firm represents) and enumerates exactly what comes back: status, Tier 1/Tier 2 completion percentages, pending match counts, and masked notified match cards. That is far more specific than the bare name 'my_clients' and is clearly distinct from siblings like my_matches or my_scorecard_status. It never states an explicit verb ('returns'/'lists'), leaving the purpose expressed as a noun phrase rather than an action.

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?

Eligibility preconditions are spelled out in detail (signed-in administrator of a consultant or PE firm, authenticator app enabled, clients that accepted the advisor disclosure). However, there is no guidance on when to choose this over my_matches, my_assessment_status, or answer_question, nor any note about when the tool is the wrong choice. Usage is implied by the audience restriction rather than stated as a routing rule.

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