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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds meaningful method-level transparency by explaining that every number comes from re-asking the feed's own predicate with one control relaxed, which tells the agent this is a computation over current state, not a guess or a static report.

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?

Two sentences carry the entire meaning with no redundancy. The first sentence fronts the results the agent can expect, and the second explains the methodology. Every word earns 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?

For a zero-parameter, read-only analytic tool, the description is complete: it lists the returned insights, explains how they are derived, and is supported by annotations confirming safety. No output schema exists, but the description sufficiently characterizes the result payload for an agent to invoke and interpret the tool.

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 has zero parameters, so the baseline is 4. The description needs to add no parameter-level meaning, and the input schema fully documents the empty parameter set. The description instead usefully explains what the output represents.

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 states a specific analytical purpose: count jobs shown by current targeting, count how many each rule hides, and identify the single change that would widen the feed most. This clearly distinguishes it from sibling tools like get_targeting, which would return targeting settings, and list_matching_jobs, which would return the jobs themselves.

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?

The description makes the use case clear: you call this when you want to understand what current targeting costs in feed reach and what one change would improve it. It does not explicitly name alternative tools or state when not to use it, so it stops short of a 5, but the context is strong enough to route an agent correctly.

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