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

Annotations already cover the safety profile (read-only, idempotent, non-destructive, closed-world), so the description's contribution is meaning: it defines lag as share of connected play over 150 ms, clarifies disconnects are 'never counted as fails', and explains where the data originates (engine netcode hooks — NGO, Mirror, ENet, Unreal net driver, WebRTC — or netSample calls). That tells the agent how to interpret an empty or partial result. It does not describe the response shape or pagination, which is the remaining 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?

Front-loaded correctly: metrics first, then breakdown dimensions, then the worst-matches pointer, then findings, then data provenance. It is information-dense rather than padded, though the long run-on sentences and heavy parenthetical nesting make it slower to scan than it needs to be.

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 9-parameter analytics tool with no output schema, the description covers what the metrics mean, what dimensions arrive, what findings look like, and where the data comes from — enough to call it correctly and interpret the result. The absence of any indication of the response structure (sections, per-finding shape) is the main thing left to the schema and guesswork.

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 schema already carries parameter meaning and the baseline is 3. The description adds only a little, chiefly the default behavior of `by` (region when the game sets a region property, otherwise any property given as `by`) and the standard breakdown dimensions. It adds nothing about env, version, session_type, steam_branch, or hours beyond what the schema documents.

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 names the precise resource (multiplayer network quality) and enumerates its constituents — ping median/slowest 5%, lag share over 150 ms RTT, packet loss, jitter, disconnects per hour by reason — plus the breakdowns and findings it produces. It distinguishes itself from siblings by pointing at glitchless_match for an individual worst match and by framing its own findings as lobby-wide vs. connection-type/region-wide, which separates it from glitchless_servers and glitchless_triage.

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?

It routes the agent outward for adjacent needs: 'glitchless_match opens one' for a worst match, glitchless_events for property values, glitchless_list_games for game ids. However, it never states explicitly when to pick this tool over glitchless_performance or glitchless_servers — the exclusions are implied by topic rather than declared.

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