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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds real value by stating that the `slug` is cosmetic and optional and that resolution happens by id, which tells the agent it can call with only a number. It stops short of mentioning rate limits, auth, or errors for missing coaches, so it is not 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 purpose is front-loaded, but a single runaway sentence then enumerates every returned field — nickname, country, win rates, trophies, upcoming matches — which duplicates an output schema that already exists. The opening also contains a duplicated word ('Get Get'), a small but visible polish defect.

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?

Everything required to invoke it is present, and the annotations plus output schema cover safety and return shape. However, the bulk of the prose explains return values that the output schema already defines, while genuinely useful calling context — behavior on invalid or ambiguous ids — is absent. Complete enough to call, not optimally allocated.

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% and both property descriptions already state that `id` is the numeric coach id and `slug` is cosmetic, so the description largely restates structured data. The one addition of substance is that coach ids live in the player id space, which clarifies how ids are derived rather than how to format them. Baseline 3 fits.

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 opens with a specific verb and resource, 'Get a Counter-Strike coach profile', and immediately narrows scope with 'Returns one coach's public HLTV profile by numeric `id`'. The note that coach ids share the player id space helps separate it from the sibling hltv_player tool, though it never names that sibling as the alternative for non-coach lookups.

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?

Usage is only implied: fetch a coach by numeric id. There is no explicit statement of when to pick hltv_coach versus hltv_player or hltv_team, and no prerequisites or failure cases (unknown id, retired coach) are described. The id-space remark is contextual trivia rather than routing guidance.

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