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

Annotations already cover the safety profile (readOnly, idempotent, closed-world, non-destructive), so the bar is lower; the description still adds real context: unverified candidates are labelled and must not be cited as authoritative, and site_ref chaining is explained. It omits practical behavior like how limit vs top_k interact or ranking/pagination results.

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-loads the resource description, then the kind breakdown, then the trust rule, then chaining — a sensible priority order with no obvious filler. The kind list is dense but each clause carries distinct information; minor run-on phrasing is the only cost.

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 15-parameter, zero-required, nested-object tool with an output schema and annotations, the description covers the main selectors, trust semantics, and chaining. The unexplained include_* toggles and limit/top_k behavior are the remaining gap an agent would have to infer.

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 53% across 15 params, yet the description compensates by giving semantic meaning to the bare kind enum (per-value behavior, which the schema lacks) and to verified_only. It leaves limit, top_k, debug, authority_level and the include_* toggles unexplained, so the compensation is partial.

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+resource ('Search the Atlasly AEC knowledge graph') and enumerates the five content kinds, so the agent knows exactly what is retrievable. It does not differentiate from plausible siblings like search_tools or inspect_research_source, which is the only thing keeping it from a 5.

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 concrete guidance per kind ('kind=sources returns official datasets by jurisdiction', 'kind=standards returns technical standards') plus a clear condition for verified_only=true. It stops short of saying when to prefer a sibling tool over this one, so no exclusions are declared.

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