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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value beyond this by disclosing the operational boundary — it returns exactly one full record and must not be used as a search/list primitive — plus the specific metadata contents of the response. It stops short of disclosing edge behaviors (e.g., behavior when an id/slug is not found), but for a read-only idempotent fetch this is a minor gap.

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 core scope ('Full metadata for one facility') is front-loaded, followed by a dense field list, usage examples, and the explicit do-not-use constraint. Each sentence earns its place — the metadata enumeration sets expectations, the examples aid parameterization, and the exclusion prevents misuse. It runs slightly long relative to a two-sentence ideal but has no filler or repetition.

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?

Given an output schema exists (so return-value details need not be restated), annotations cover the safety profile, and parameter coverage is 100%, the description is complete. It communicates scope (one facility), the do-not-use-for-searching boundary, usage examples, and the specific data returned. An agent has everything needed to invoke it correctly for a read-only, idempotent lookup.

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%, so the baseline is 3. The description adds value beyond the schema by providing concrete, realistic example values (equinix-dc1-ashburn, digital-realty-iad8) that show an agent what valid id/slug look like, and reinforces that id is an alias for facility_id from a prior search result. These examples meaningfully help an agent populate the lookup parameters correctly.

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 ('Full metadata for one facility'), enumerates the exact fields returned (operator, address, lat/lon, MW total/used, cooling type, fiber carriers, commissioning year, status, DCPI verdict, peers), and answers concrete questions ('who operates this data center and how big is it'). It clearly distinguishes from the search_facilities sibling by emphasizing it returns exactly ONE facility, so an agent can tell them apart without opening schemas.

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?

Provides explicit when-to-use guidance with two working examples ('Try: get_facility id=equinix-dc1-ashburn — or get_facility slug=digital-realty-iad8') and an explicit exclusion with the named alternative ('do NOT use to search or list many facilities (use search_facilities)'). Nothing about when to use it vs alternatives is left to inference.

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