Summarize replay coaching trends

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

Annotations already declare readOnlyHint=true, so the description does not need to restate safety. The 'locally persisted' wording adds useful context that the tool reads stored analyses rather than triggering new replay processing, but it says nothing about freshness, computation, or how results are derived.

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 description is a single efficient sentence with the core operation front-loaded and no filler. It is concise, though the brevity contributes to the lack of parameter and usage detail handled in other dimensions.

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?

The core purpose and data source are clear, and the output schema presumably covers return shape, but three optional parameters are completely undocumented and no usage guidance is offered. For a tool with a bare schema, this leaves important operational context missing.

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 0%, yet the description gives no explanation of limit, profile_id, or team_version. An agent cannot tell whether profile_id and team_version scope the aggregation, how limit affects the output, or which parameters are relevant to a given request.

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 uses a specific verb, 'aggregate', and clearly names the resource: recurring strengths, improvement findings, and results across locally persisted replay analyses. This distinguishes it from single-replay tools like vgc_replay_analyze and vgc_replay_get.

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 phrase 'across locally persisted replay analyses' implies this is for summarizing existing stored analyses rather than analyzing a single replay. However, there is no explicit statement about when to use this tool over alternatives like vgc_replay_get or vgc_replay_turn, and no exclusions are provided.

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