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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds substantial beyond-schema behavior: the status state machine (pending/interpreting/processing = still working), an anti-polling constraint, the missing_company_name fallback path, and the caveat that company rows are samples rather than exhaustive matches.

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?

Four dense sentences, no filler, and the primary use case is front-loaded. Slightly crowded — the results.next_page phrasing references an output field by path in a way that reads a bit awkwardly, but every sentence carries actionable information.

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 needn't be described, and the description fills the remaining gaps: status states, pagination source, the missing_company_name edge case, and the partial-results caveat for company rows. An agent has everything needed to call this correctly and know when to stop.

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 25% (only 'page' is documented in the schema), so the description should carry more weight. It does clarify 'page' as coming from results.next_page and adds meaning to 'view' via the jobs/companies rows, but 'sort' is never addressed and the schema enums are left to speak for themselves.

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 names a specific verb and resource ('Read a search and its results') and enumerates the three concrete sub-operations: view switching between jobs/companies and fetching results.next_page. It also implicitly separates itself from search.create by warning not to create another search while one is processing.

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 explicit when-to-do-what rules: pending/interpreting/processing means wait and don't poll rapidly, and if missing_company_name is set the agent should ask for the careers URL and route to companies.submissions.create. That is an explicit alternative-tool routing decision, not just context.

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