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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, but the description adds substantial behavioral context: a 4.5-second latency guarantee, a paid LLM path, an extractive fallback marked via "synthesis":"extractive", and a no-invented-facts sourcing constraint. It does not contradict any annotation.

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 promise and then layers on relevant execution details. It is somewhat dense and includes a sample endpoint suggestion, but most sentences contribute useful information.

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 description explains the output format despite an output schema existing, and covers fallback behavior well. It leaves some contextual gaps around payment/auth requirements and sibling routing, but it is largely complete for invocation.

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 both query and max_sources are already documented. The description reinforces the question-and-sources framing but does not add syntax, constraints, or examples beyond the schema, making the baseline of 3 appropriate.

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 states a specific outcome: ask a question and get a cited answer with claims verified against sources. It clearly identifies the resource and output better than a simple search, but it does not explicitly distinguish itself from siblings like search, ask_model, or fact_check.

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 implied use case is clear: submit a research question when you need a cited, synthesized answer. However, there is no explicit guidance on when to choose this over siblings such as search, ask_model, fact_check, or verify, and no exclusions or prerequisites are given.

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