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

Annotations already declare this is a non-destructive, idempotent mutation, so the bar is lower. The description adds real value beyond them by disclosing preservation semantics: edited names, descriptions, and on/off choices survive the recompile. It still omits failure behavior and whether the compile is blocking.

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 short sentences, front-loaded with the core action, followed by the key preservation guarantee and the required next step. Nothing is wasted and no sentence is redundant with structured fields.

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 four-parameter mutation tool with no output schema, the essential idea (recompile, preserve edits, then check issues) is conveyed. Gaps remain around spec-source precedence, error outcomes, and the undocumented spec_file_id, which an agent would need before calling it confidently.

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%, so the description has to carry weight. It explains that spec content can come from source_url or spec and that omitting both reuses the existing spec, but it never mentions spec_file_id or states precedence when multiple spec sources are supplied, and it says nothing about gateway_id.

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 ('Compile the gateway again') and clarifies the two modes: from a new spec or the existing one. The word 'again' distinguishes it from create_gateway/update_gateway, though it never names those siblings explicitly.

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 implies when to use it (supplying a new spec vs. recompiling the current one) and mandates a follow-up call to list_gateway_issues, which is genuinely useful routing. However, it gives no when-not guidance and does not contrast with update_gateway or fix_gateway_issues, which are plausible alternatives.

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