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

Annotations already cover read-only, idempotent, closed-world safety, so the description is free to add the genuinely useful behavior: it discloses the empty-state ("Says so when no strategy exists yet") and explains how cells are keyed. That empty-state note is the kind of thing an agent can't get from annotations and matters for deciding whether to seed a strategy instead.

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-loads what the strategy contains, then the cell-key mechanics, then the empty-state note. Dense and run-on in places but every clause carries information; no filler sentences.

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?

With no output schema, the description carries the burden of describing the return value, and it does so well: entity types, ids, cell composite keys, and the not-yet-created case. Only minor gap is not indicating what happens with an invalid site_id.

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 description coverage is 100%, so both site_id and user_goal are fully documented in the schema. The description adds no parameter-level detail beyond that, which is fine but earns only the baseline.

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+resource ("the site's audience strategy") and enumerates exactly what it returns: personas, buying stages, pain points, competitors with ids, plus cells with messaging briefs. The cell-key format is spelled out, so an agent knows precisely what object it is fetching and can distinguish it from seed_marketing_strategy or materialize_strategy_cell.

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?

Implies usage with "Campaigns and landing pages start from a cell," which tells the agent this is a prerequisite read before drafting campaigns. However, it never states when to call this versus seed_marketing_strategy, run_marketing_scan, or infer_strategy_cell_from_ad, and gives no exclusions or prerequisites.

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