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, and the description is consistent with a session-mutating, non-destructive call. It adds real context beyond the annotations: a deprecation timeline with notice cadence, a migration doc, and the PECR/UK GDPR Article 6(1)(f) constraint that audiences are corporate-subscribers-only by default unless a toggle changes. It stops short of describing what the session count returns or how session state accumulates across calls.

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 'Deprecated' so the agent sees the critical signal first, and the migration path follows immediately. The closing PECR/sole-trader sentence is long but earns its place because it changes what results mean; the notice-cadence detail ('after three emailed notices') is the one clause that could be trimmed.

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, annotations cover the safety profile, and there are no parameters, so the description only needs lifecycle, replacement, and compliance context — all three are present. Nothing an agent needs to decide whether to call this tool, or to interpret its results, is missing.

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?

Zero declared parameters, so the baseline is 4; the schema itself notes the arguments are the old tool's, unchanged, and that the adapter maps them. The description only implies the arguments are filters ('adds filters to a count'), leaving the actual accepted keys to the external migration document rather than spelling any out — a minor gap against an otherwise complete schema description.

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 and mechanism — 'adds filters to a count held in the server session' — which precisely distinguishes it from count_audience (whole definition in one call, no session state) and compile_audience (turns a brief into a definition). An agent can identify what this does and what it is not without opening any 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?

Explicitly routes the agent away from this tool: 'Use compile_audience, then count_audience instead,' and explains why (no session state to build up). It also gives the hard cutoff (12 months after launch, after three emailed notices) and a migration URL mapping every call, so both the preferred alternative and the escape hatch are named.

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