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

Annotations already declare a non-read-only, non-destructive, idempotent, closed-world mutation, but the description adds real behavioral context beyond them: changes are confined to the draft (not the published gateway), each call performs only a few AI rewrites so the operation is intentionally partial/batched, and the response enumerates before/after pairs. The one gap is that permission requirements and whether draft changes can be discarded are not stated, which keeps it below a 5.

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?

Front-loaded with the action and its source, then effects, then the mutation scope, then the iteration rule and the alternative — a sensible priority order with no filler. The colon-chained clauses make it slightly dense to parse, but every sentence carries distinct 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?

For a mutating, batched tool with no output schema, the description covers the essentials: what changes, that only the draft is touched, what the response contains, and how to finish a multi-call sweep. It would be complete at 5 if it noted whether the draft must later be published or can be rolled back after fixes are applied.

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% and both optional filters already carry descriptions with defaults ('every affected tool', 'every issue with an auto_fix'), so baseline is 3. The description adds a little framing by tying issues to list_gateway_issues, but it never explains the interaction between tools/issue_ids or what gateway_id must reference, so it does not meaningfully enrich parameter meaning 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 ('Apply the auto_fix of the issues from list_gateway_issues') and enumerates the concrete effects: turning off deprecated/destructive tools, legalizing names, rewriting names and descriptions. It also distinguishes itself from two siblings by name — list_gateway_issues as the source of fixes and update_gateway_tools as the manual alternative — so an agent can route correctly without opening any 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?

Gives an explicit prerequisite ('after the person agrees'), an explicit alternative for a different intent ('To use your own names or descriptions, use update_gateway_tools instead'), and an explicit continuation rule ('call again while remaining is set'). When-to-use, when-to-use-something-else, and iterative-call guidance are all covered.

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