vision_stats

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

The description carries the full behavioral burden because no annotations are provided, yet it only states it 'Return(s) cumulative... usage.' The word 'Return' implies a non-destructive, read-only action, and 'cumulative' implies an aggregate view, but the description does not explicitly say the call consumes no vision API budget, whether results reset per session, or the shape of the returned data. This is adequate but thin.

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?

A single, front-loaded sentence that names the resource ('vision API usage'), the aggregation ('cumulative'), and the exact fields. There is no fluff or repetitive text, and the sentence is highly scannable.

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?

Given the simple shape (0 required parameters, no output schema), the description covers the semantics of the resource and the fields returned. A slightly stronger context would be an explicit note that this is about the current session and correlates with vision_budget, but the existing session hint in the schema plus the description keeps it mostly complete.

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 'session' and 'lease' have rich descriptions already (session name guidance and unique-name advice, lease token threading note). The description adds only the session-scoped value of the returned fields and does not further explain parameters, so it stays the baseline 3 with schema doing 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?

The description names a specific verb and resource ('Return cumulative vision API usage') and lists the exact fields returned (calls, cache_hits, tokens, cost_usd) plus the session scope. This clearly separates it from vision_click/vision_find/vision_type, but it never mentions the closest sibling, vision_budget, so it doesn't fully differentiate against the budget/usage related tool.

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?

There is no guidance on when to use this tool versus a sibling such as vision_budget, vision_clear_cache, or vision_find. An agent gets no explicit 'use when' or 'use instead of' hint beyond the bare role of returning usage stats, leaving the selection to inference.

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