Research a topic

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial behavioral detail: nothing is saved, it consumes AI credits and costs per call, runs noticeably longer than a plain read, produces non-deterministic results, and returns prose rather than structured JSON. This goes well beyond the annotations without contradicting them.

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 front-loaded with the core purpose, then each subsequent sentence adds a distinct practical point: when to use, alternatives, side effects, cost, runtime, non-determinism, output format, and verification caveat. No sentence is wasted.

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 generative, non-deterministic tool with no output schema, the description is remarkably complete. It covers return shape, side effects, cost, timing, determinism, and how to verify output, plus differentiates from sibling tools. This is more than sufficient for an agent to select and invoke the tool 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?

The single parameter `query` is fully documented in the schema, including length constraints and a concrete example of specificity. The description does not need to add much parameter-level detail, so the baseline of 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?

The description opens with a specific action verb and resource: 'Research a topic with AI and return insights, sources, and a suggested content outline.' It clearly distinguishes itself from siblings by stating it is not a finished article, not for titles (use generate_title_seo), and not for checking existing content (use search_articles).

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?

The description gives explicit when-to-use guidance: 'Use it at the START of a piece, before drafting.' It also names direct alternatives for related tasks and states that the tool produces raw material, not a finished article or title.

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