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

With no annotations at all, the description carries the full disclosure burden and handles it remarkably well. It reveals the safety profile ('No real-world side effects'), the entitlement condition ('reading THIS LIST is Pro as of 2026-08-31'), the cost profile ('cost nothing to call'), and the verification guarantee ('example_request URL that returned HTTP 200 to an unauthenticated GET'). This is substantive behavioral context that an agent cannot infer from the schema.

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?

At roughly 105 words, it is dense but not bloated — every clause adds new information (safety, cost, entitlement, side-effect profile, verification status, use cases, grouping default). The most decision-relevant framing ('SAFE TO EXPERIMENT WITH') is front-loaded, and the use-case list and grouping note come after. It is slightly long, but the length is justified because there are no annotations or output schema to offload information to.

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 5-parameter tool with no annotations and no output schema, the description provides the core contract: what the list contains, the guarantee behind each example_request URL, the entitlement caveat, and how grouping changes the result set. The main gap is the return envelope — the description never states whether the response is a simple array or wrapped object, and pagination behavior with the limit parameter is unspecified. Still, the missing pieces are minor relative to how much is disclosed.

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 80%, so the baseline is 3, but the description adds meaning beyond the schema. It explains the 'no-key' vs 'instant-key' distinction operationally ('callable right now' vs 'free self-serve key') for the access parameter, and it enriches the grouping parameter by revealing that deep-archive means 'institutional/OAI-PMH repositories' — information absent from the schema's bare enum. The limit parameter is self-documenting via default/min/max, so no description is needed.

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 names a specific resource — curated APIs that are SAFE TO EXPERIMENT WITH — with a clear verb (get/list) and defines what distinguishes this tool from sibling search tools like find_apis and apis_io_search: it returns a pre-verified, harmless subset rather than general search results. The 'UNDERSTANDING' category prefix and the concrete properties (no key, free, no side effects) make the tool's identity unmistakable.

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 gives explicit when-to-use scenarios: 'new to this catalog, learning what an API call feels like, testing a tool-use loop, or need a harmless endpoint to demonstrate something.' These are concrete trigger conditions. However, it does not name a specific alternative tool for the opposite case (e.g., when you need production-grade APIs or full search), nor does it say when not to use it — leaving exclusions implicit.

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