Find Alternative Facilities

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

Annotations already carry the read-only, idempotent, non-destructive safety profile, lowering the burden. The description adds genuinely useful behavior beyond that: it returns ranked alternatives with similarity_score, match_reasons, and key_differences versus the target, and it clarifies discovery semantics versus scoring/comparison. However, it stops short of disclosing default radius/limit or empty-result behavior, and it does not surface the silent key-stripping behavior that the schema itself flags.

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 structure is sound — use case first, then a worked example, then returns, then exclusions — and the exclusion clause is efficient. But the param-summary sentence is stale and factually wrong against the schema, so one of the four sentences is positively harmful rather than earning its place. Slightly over-packed for what it conveys.

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 an output schema present and 100% param schema coverage, the burden shifts to usage context, which the description covers well: when to use, what it returns, and what to use instead. The critical gap is the inconsistent param list, which could cause an agent to invoke it with invalid arguments (name, capacity_mw) that are silently stripped. For a simple read-only tool this is a notable but not fatal completeness defect.

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%, giving a baseline of 3, but the description's param summary actively misleads: it advertises 'facility_id or name' and 'optional capacity_mw' while the schema explicitly states 'there is no `name` param; an undeclared key is silently stripped' and contains no capacity_mw property at all. It also omits the real optional params match_on and exclude_operator. An agent following the description would pass phantom keys and get them silently dropped.

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 anchors on a specific verb+resource — discovering alternative facilities similar to one seed facility — and illustrates it with a concrete query example ('Find alternatives to the Ashburn QTS campus for about 50MW.'). It also names what it is not (score_facility, analyze_site, compare_sites), so an agent can distinguish it from siblings at a glance.

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 trigger condition is explicit and front-loaded ('when a user likes ONE specific facility and wants similar nearby options'), and the exclusion clause names the exact alternatives to use instead ('use score_facility or analyze_site' for single-site scoring, 'use compare_sites' for head-to-head short-list comparison). The closing line — 'this DISCOVERS candidates from a single seed facility' — leaves no ambiguity about when to invoke it.

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