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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the safety bar is covered; the description adds the non-obvious trait that the filters live in the server session rather than in arguments, which is essential given zero parameters. It further discloses the sunset deadline, the PECR audience-scope default (corporate subscribers only, sole traders and ordinary partnerships excluded unless the toggle changes) and the lawful basis — real behavioral context an agent cannot infer from annotations.

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?

The deprecation and the replacement tool are front-loaded, then sunset terms, then legal scope, which is the right ordering. The GDPR/PECR sentence is long and only marginally actionable for an agent calling a deprecated endpoint, so a small amount of the text does not fully earn its place.

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, so return values did not need spelling out, yet the description still names the payload contents. Combined with the sunset timeline, migration pointer and audience-scope caveat, nothing an agent needs in order to call this correctly 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?

With zero parameters the baseline is 4, and the description goes one step further by explaining why there are none: filters are held in the server session. The schema's own description covers the adapter mapping, so no additional per-parameter detail is needed or missing.

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 first clause states a specific verb and resource (returns the count), immediately flags the tool as deprecated, and names the replacement count_audience. An agent can distinguish it from list_audiences, preview_records and the other siblings 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?

It gives an explicit directive to use count_audience instead, plus the exact sunset condition (12 months after the new tools launch, after three emailed notices) and a migration URL that maps every call. There is no ambiguity about when this tool should still be selected.

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