faz_start_log_search

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

Annotations include readOnlyHint=false and openWorldHint=true; the description adds that the operation is asynchronous, returns a task ID that must be polled later, and warns that using All_FortiGate can be resource-intensive. This goes beyond the annotations without contradicting them. It doesn't mention rate limits or required permissions, but those are not essential here.

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?

Three sentences, front-loaded with the core purpose, and each sentence earns its place. The structure efficiently conveys the async contract, time-range modes, device caution, and the required follow-up action with zero waste.

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 tool has an output schema, so return values need not be described. The description covers the async contract, next step (faz_get_log_search), and key parameter interactions. It leaves adom context and cancellation behavior to sibling tools and schema, which is a minor gap for full self-sufficiency.

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 has 10 parameters with 0% description coverage. The description partially compensates by clarifying the mutual exclusion between start_time/end_time and last_n_hours, and by explaining the device list and All_FortiGate specialness. However, it does not explain adom, filter_expression syntax, time format, or the meaning of log_type/time_order beyond what the schema's enum/default values already show.

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?

Description opens with 'Start an asynchronous LogView search and return its task ID' – a specific verb, resource, and return contract. This clearly distinguishes it from sibling faz_get_log_search (retrieves results) and faz_search_logs (likely synchronous) by emphasizing the async and ID-returning nature.

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?

Provides explicit usage conditions: device names must be explicit, All_FortiGate is discouraged unless intentional, and start_time/end_time must be supplied together or last_n_hours is used. It also names the next step, 'Call faz_get_log_search next'. It does not explicitly say when to prefer this over faz_search_logs, but the async workflow is clearly implied.

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