deep_research_topic

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description usefully adds that execution is 'autonomous' and 'multi-pass', hinting at a long-running unattended process. It omits latency/duration expectations and any async polling cue (notably absent despite a check_research_status sibling), so it adds modest value only.

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?

A single front-loaded sentence that opens with the trigger ('Use when...') and packs the output type and scope with zero filler. Nothing is redundant and the most decision-relevant information leads.

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 6-parameter tool with full schema coverage and safety annotations, the description covers the what and when adequately. It does not signal the likely long-running/async nature of an autonomous multi-pass job, which an agent needs in order to call it correctly. With no output schema, a brief note on what is returned (beyond 'briefing report') would have closed the gap.

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 query, mode, depth, sub_themes, userId and graphId are all already documented in the schema with enums and usage notes. The description contributes no additional parameter guidance, so the baseline 3 is 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?

States a concrete deliverable (an 'exhaustive, autonomous multi-pass briefing report') and its ingredient sources (cross-graph trends, corporate disclosures, expert perspectives), which is far more specific than a bare 'research' verb. It implicitly separates itself from lighter siblings like brainstorm_topic or search_graph. It stops short of naming the alternatives it is not, so it lands at 4.

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 whole description is a single use-condition ('Use when the user needs an exhaustive... report'), which gives a clear trigger. However, it offers no exclusions, no prerequisites, and does not route the agent away from cheaper siblings such as brainstorm_topic or discover_adjacent_trends. Usage is implied rather than fully specified.

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