bi_list_alerts

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

Annotations already provide readOnlyHint=true, and the description adds meaningful behavioral detail beyond that: no dedup, per-alert timestamps and memos, flexible date format parsing, default limit, and the important flagged-view crossover where clip items lack 'zones' and 'msec' means clip length instead of alert length. This exceeds what annotations alone communicate.

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 dense but well-organized: front-loaded output summary, then usage guidance, then parameter formats, then the critical crossover edge case. Every sentence contributes distinct information, and it links to the schema for the full view enum rather than duplicating it.

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 7-parameter list tool with no output schema, the description covers the essential operational context: what is returned, when to use it, date formats, filters, default limit, and an important view-related anomaly. A small gap is the lack of explicit response shape or ordering/pagination behavior, but the high schema coverage and readOnly annotation reduce the need for more.

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 baseline is 3. The description adds value beyond the schema by specifying the accepted formats for startdate/enddate (unix epoch int, ISO-8601, relative shorthand with examples), explaining that 'search' is a server-side memo substring, noting the 'Index' sentinel for camera, and giving the default for 'limit'. It does not redundantly restate every schema property.

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-resource combination ('Recent alerts...') and clearly states what the tool returns: AI memo (object, confidence, license plate), zones triggered, and clip path. It also distinguishes itself from nearby siblings by naming bi_list_log as the alternative to use after this tool and by calling itself the 'First stop' for alert-chain reconstruction.

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 explicitly says when to use this tool ('First stop for what fired when / reconstructing an alert chain') and when to prefer another ('Use this before bi_list_log when investigating a specific event'). The crossover note about 'flagged' view potentially returning clip items also warns the agent about a case that would otherwise look like a different tool's domain.

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