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

Even though annotations already declare readOnlyHint=true and destructiveHint=false, the description adds substantial context: it is read-only, never auto-fixes, includes a permission error for unauthorized callers, and explains that the trends parameter adds history for before/after comparison. This is exactly the kind of behavioral disclosure that helps the agent reason about invocation safety and expectations.

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?

The description is information-dense and every clause adds value, but the opening sentence is a long run-on that packs many report sections together. It is front-loaded with the critical 'ADMIN/CURATOR ONLY' caveat, and the content is well-organized overall, but it could be broken into bullet-like sentences for easier parsing.

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 complex report tool with no output schema, the description thoroughly covers what the report contains (funnel, backlog, asset list, health, failure patterns, queue state, alerts), the permission prerequisite, read-only behavior, and optional trends expansion. This gives the agent enough context to invoke it appropriately and understand what to expect in the result.

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 parameters are already well-documented. The description goes beyond the schema by specifically explaining the purpose of the 'trends' flag in the context of 'did my change help?', and clarifies the default output is 'toon' as the token-efficient format. It does not add as much depth for 'format' and 'trend_days', but it appropriately complements 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 clearly states this tool provides a machine-readable health report of the autario data engine, listing its exact scope (ingestion funnel, dirty backlog, asset coverage, etc.). It distinguishes itself from sibling tools by focusing specifically on the engine health as rendered by /admin/health and /admin/storage, and is unambiguous about its resource and purpose.

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 explicitly states this is ADMIN/CURATOR ONLY and requires OAuth authorization as the curator account, warning that any other caller gets a permission error. It also gives concrete usage triggers ('Use when asked...' followed by five specific questions), which is excellent guidance for when to choose this tool over alternatives.

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