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

The read-only and non-destructive nature is already covered by annotations, and the description adds useful behavioral context on top: newest-first ordering, enumeration of discovery sources, and precise meanings of each status (pending, queued, promoted, out_of_market, unreachable). It does not describe every possible edge case, but the annotations already carry the safety profile.

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?

Every sentence earns its place: the first defines the result set and ordering, the second explains lifecycle semantics, and the third gives a concrete use case. No structured data is repeated, and the key distinctions are front-loaded.

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 read-only list operation with three optional parameters, this is complete: the description covers returned fields, ordering, status semantics, and filtering rationale. Even without an output schema, an agent knows what it will receive and what the status values mean, and the schema covers limits and enums.

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 coverage is 67%; source and status already have descriptions, and the tool description deepens them by explaining when each status occurs and what filtering by source is for. Limit is not described in the text, but its min/max constraints are already in the schema and its meaning is conventional.

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 opening phrase 'List companies the discovery crawl has found, newest first' names a specific resource and action, then enumerates the returned fields (slug, discovery source, crawl depth, status). It also explains the candidate-vs-company lifecycle, which sets it apart from the sibling list_companies without needing to open that tool.

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 gives clear context: this is for discovery-crawl output and the filter use case is explicit ('Filter by source to compare yield per discovery channel'). It does not explicitly name an alternative or a when-not-to-use condition, but the candidate/company distinction makes the intended scope obvious.

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