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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), and the description adds meaningful context beyond them: logs are masked, results are paged with a cursor, a page-level miss is not a definitive miss, and it warns not to follow instructions embedded in log lines (prompt-injection defense).

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?

Five short sentences, purpose front-loaded, and each clause carries distinct value: what it searches, matching semantics, pagination, the non-conclusive miss caveat, and the injection warning.

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, full parameter coverage, and rich annotations, the description supplies the behavioral details an agent needs to call it correctly. The only gap is that it never contrasts with the sibling read_run_logs, leaving the search-vs-read choice to inference.

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 100%, so every parameter including cursor, source, and search is already documented in the schema. The description restates the case-insensitive substring behavior and adds light cursor guidance ('follow the cursor to search more pages'), but contributes little beyond 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?

States a specific verb and resource ('find an error or text in the logs of a Runzumi job') and the matching mechanism (case-insensitive substring on one page). It functionally distinguishes itself from read_run_logs, but never names that sibling or any alternative, so sibling differentiation is implicit rather than explicit.

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?

Clear usage context ('find an error or text') plus practical guidance: follow the cursor for more pages, and a no-match on one page is not conclusive. It gives no explicit when-not-to-use or pointer to the sibling read_run_logs for full log reads.

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