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

Annotations already carry readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real content the annotations cannot: the shape and granularity of results (clustered positions, per-spot death share, top cause, rage quits) and the scope of level-level context returned. It does not mention look-back defaults or data-retention effects, which is the main 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?

Two sentences, front-loaded with the result content, then the use case. The parenthetical enumeration is dense but every element names an actual returned field rather than padding.

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 no output schema, the description carries the return-value burden and does so adequately by listing the cluster fields and level stats. For a nine-parameter read tool with full schema coverage, the missing piece is mostly the retention/look-back framing, which the hours param documents instead.

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 description coverage is 100%, so the schema already explains level, hours, env, props, session_type and the rest with examples. The description only implies that a level must be supplied and does not add syntax or behavioral detail about the nine filters. Baseline 3 applies when the schema does the heavy lifting.

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 subject and content: 'clustered death positions in world coordinates' with named fields (x range, share of deaths, top cause, rage quits) plus level bounds and completion stats. That is clearly distinguishable from sibling analytics tools like glitchless_overview or glitchless_session, though it never names a sibling explicitly to draw the contrast.

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?

'Use it to find difficulty spikes, then look up the level data around those coordinates' gives a use case and a follow-up workflow, but names no alternative tool and states no exclusions. The agent gets implied usage rather than an explicit when/when-not rule.

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