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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world. The description adds genuinely new behavior: following applies to future openings only, does not collect historical matches, and does not attempt to submit an unknown careers page. It does not address what happens on a repeat follow of an already-followed company, despite idempotentHint=false.

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?

Three tight sentences, front-loaded with purpose, followed by sourcing guidance and then scoping caveats. No filler and no repetition of schema content.

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 an output schema present, return values need no explanation, and the description covers the two hard parts: where company_id comes from and what the filters mean. Missing only the repeat-follow behavior for a non-idempotent mutation, which is a minor gap.

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 only 50% and company_id has no schema description, but the description compensates by explaining its three valid sources. The filter guidance ('specify at least one match', '[{}] follows all new openings') reinforces the minItems semantics, though most detailed filter semantics already live in the schema.

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 verb and resource ('Follow an indexed company') plus the concrete payoff ('future matching openings and company recommendations'). It also distinguishes itself negatively from a related action ('does not submit an unknown careers page'), so an agent can separate it from companies.submissions.create without opening the 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 tells the agent where company_id must come from (Search, a ready submission, or a recommendation candidate_company.id) and how to express a catch-all follow ('[{}] follows all new openings'), plus an explicit exclusion. It stops short of naming a sibling alternative for the case where the user wants historical or ad-hoc matching.

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