agent

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

Annotations already cover the safety profile (readOnly, openWorld, idempotent, non-destructive), and the description layers real operational detail on top: the exact pipeline stages, parallel execution within budget, per-step timing via steps[], MCP sampling with a keyword-extraction fallback, and a warning not to surface the raw step log as a result. This is the kind of behavior the annotations cannot express.

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?

Purpose is front-loaded in one sentence, then organized into step-transparency, parameter, pipeline, and return sections — appropriate density for a 9-parameter tool. Minor redundancy: "Full step transparency" and the steps[] sentence in the pipeline block make the same point twice.

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 discharges that burden by enumerating the return shape (result, sources[], pages_fetched, steps[], total_time_ms, sampling_supported) and explaining degraded-mode output. What's missing is failure/partial-result behavior and any notion of source-quality limits when the budget is exhausted.

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 the baseline is 3 and the schema already explains every param including citation_format's enum values. The description mostly restates defaults already present in the schema (max_pages 10, max_time_ms 60000) and adds only a single illustrative example for prompt, so it does not meaningfully exceed the schema.

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 opening line states a specific resource and action: natural-language data gathering across sources, with the plan → fetch → extract → synthesize pipeline spelled out. An agent understands exactly what it gets back. However, it never names a sibling (research, search, crawl, fetch) to differentiate itself, despite 'research' sounding functionally close.

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?

Usage context is implied through the example prompt ("pricing for the top 5 CRM tools") and the guidance on when synthesis is vs. isn't available, plus the instruction that the caller must write the summary from returned evidence. But there is no explicit when-not-to-use-this and no routing statement against the near-siblings 'research', 'search', or 'crawl'.

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