Deep search dossier (SearXNG)

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

Annotations already cover readOnly/openWorld/idempotent, yet the description adds substantial context: the SSRF guard on fetches, synthesis only when SEARXNG_SYNTHESIS_URL is set (otherwise excerpts only), and the task-handle vs inline-blocking behavior depending on tasks capability negotiation. It also flags returned web content as untrusted and warns against following embedded instructions.

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 core purpose is front-loaded in the opening clause, and each sentence carries distinct information (synthesis config, task handle, usage scope, injection warning). The single dense paragraph is efficient, though slightly packed.

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: a cited dossier, excerpts-only when synthesis is unconfigured, or a task handle to poll. Config dependencies and async behavior are disclosed, so an agent has what it needs to call it correctly.

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 all four parameters are already documented in the schema. The description's phrases like 'rounds' and 'sources fetched per iteration' restate what the schema already says, adding no syntax or format detail beyond it. Baseline 3 applies.

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 verb and resource: 'run an iterative research loop' producing a 'cited dossier'. The clause 'for questions that need several sources read, not one page' functionally separates it from single-shot siblings like search and fetch_content, though no sibling is named outright.

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 for questions that need several sources read, not one page' gives a clear when-to-use and implies when-not. It stops short of naming an explicit alternative tool to route to, so the alternative is only implied.

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