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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds genuinely new behavior by disclosing partial-failure semantics ('an unknown id is omitted from the item list'), which tells the agent not to expect an error or a positional placeholder. It also enumerates what a full hub object contains, so the agent knows the payload breadth versus the summary tool. It stops short of noting payload size or rate-limit implications of a 20-id bulk call, which keeps it off a 5.

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 routing facts (what it returns, the cap, the sibling contrast) are front-loaded in the first two sentences, and the trailing field enumeration is dense but purposeful for choosing between full and summary reads. The long comma-separated field list is slightly heavy and could be trimmed, 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?

For a one-parameter bulk read with a declared output schema and safety annotations, the description covers purpose, alternatives, cardinality, and unknown-id handling — everything needed to invoke it correctly. Return-value details are unnecessary given the output schema, and the only miss is any note on result ordering or payload size at the 20-id limit.

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?

With schema description coverage at 100% and a single parameter, the schema already explains that ids is a required array of hub UUIDs capped at 20. The description restates the same 20-id cap and does not add format or syntax detail beyond it, so it clears the baseline but adds little marginal meaning.

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 and resource ('Get FACEIT full hub objects'), the cardinality cap ('up to 20 ids'), and the transport ('v2 bulk read'). It then explicitly disambiguates from two siblings: faceit-hubs serves summaries and faceit-hub serves one id. An agent can select this tool without inspecting 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?

The 'Unlike faceit-hubs (summaries) and faceit-hub (one id)' clause names the alternatives and the exact condition that selects this one — needing several FULL hubs in a single call. The 20-id ceiling is also stated as a practical boundary, leaving little to inference.

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