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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint false), the description adds meaningful behavioral context: the tool is read-only and never auto-fixes, fixes must be done by a human or an engine change, and the caller must be OAuth-authorized as the autario curator account or receive a permission error. It also says the report matches /admin/health and /admin/storage but is provided as data rather than screenshots. This is valuable behavioral disclosure that annotations alone do not provide.

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 dense but front-loaded with the admin-only warning and the core purpose, and every major section (contents, behavior, auth, use cases) adds value for a complex admin tool. However, the single long paragraph packs many clauses together and could be tightened slightly. For example, 'This is the same report... as data you can reason over instead of screenshots' could be shortened. Still, it is appropriately informative for a tool with no output schema.

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?

This is complete for a complex admin-only health tool with no output schema. It covers access requirements, permission failure mode, the full inventory of report sections, the read-only no-auto-fix behavior, the trends option, and the exact questions that should trigger its use. An agent can confidently decide when to call it and what to expect without needing additional context from siblings or structured metadata.

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?

All three parameters are fully described in the input schema at 100% coverage, so the description does not need to repeat their mechanics. The description reinforces the purpose of trends ('did my change help?') but adds little beyond the schema's own explanation of trend_days and format. This matches the baseline 3 for high schema coverage.

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 states a specific verb and resource: get the machine-readable health report of autario's ingest engine. It enumerates the exact contents (ingestion funnel, dirty backlog, shadow-column coverage, per-provider health, failure patterns, queue state, alerts) and clearly marks it as ADMIN/CURATOR ONLY, which distinguishes it from general data tools in the sibling list. This is far from a tautology and leaves no ambiguity about what the tool does.

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 provides clear trigger phrases ('how is the engine doing', 'what is broken', 'did the last fix work') and states that only OAuth-authorized autario curator callers can use it, with all other callers receiving a permission error. It also contrasts the tool with /admin/health and /admin/storage by emphasizing machine-readable output. It does not explicitly name sibling MCP tools as alternatives, so not a full 5, but the context is strong.

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