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

Annotations already cover read-only, idempotent, open-world and non-destructive, yet the description still adds real behavioral context: the response shape (warehouse_lookup_plan, verified_sources, missing_categories, confidence), the scope exclusion of live constraint fetching, and the site_ref chaining contract. It stops short of describing how routing is decided or what an unresolved/partial site does to the route.

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-loaded with the core purpose, then the usage condition, output names, exclusion and chaining note — each sentence carries distinct information. Slightly dense blocks (the chaining sentence packs six reused fields) but nothing is redundant filler.

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?

With rich annotations, an output schema and a nested site_ref object, the description covers purpose, timing, exclusions and chaining, which is most of what an agent needs. The one meaningful omission is the input-precondition story — that address or site_ref is effectively required — for a tool declaring zero required parameters.

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 description coverage is 83%, so the schema already documents address, question, categories, include_candidates and site_ref semantics in detail; the description only reinforces the site_ref hand-off. It does not clarify the interaction between address and site_ref (or that with zero required params at least one of them must be supplied), which is the main ambiguity an agent faces.

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 ("Resolve a site into a structured data-source route") and enumerates the four things it determines, so the agent knows exactly what comes back. It also draws a hard boundary against the per-constraint siblings ("Does not fetch live constraint data"), making it distinguishable without opening any schema.

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?

"Use before making planning analysis claims" gives explicit timing, and the negative guidance ("use per-constraint tools for that") states when not to use it. The gap is that the alternative is only named as a class ("per-constraint tools") rather than pointing at concrete siblings like check_planning_constraints or get_flood_risk.

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