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

The description adds some useful behavioral context beyond the annotations, such as the agent planning its strategy, searching multiple graphs, validating with institutional data, and automatically including earnings-call and macro/supplemental data. However, with sibling tool check_research_status present and no output schema, the description is ambiguous about whether this launches an asynchronous session whose results must later be fetched, which is an important behavioral detail. The annotations already declare this as read-only, so no contradiction results, but the missing async handoff weakens transparency.

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?

This long description is firmly front-loaded with the action and deliverable, followed by use-case guidance and a clear 'don't call other tools' note. Each sentence provides substantive information. It is a bit verbose compared to minimal examples, and the middle strategy sentence could be condensed, but overall the structure and urgency are strong.

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?

Given the tool's complexity, the schema covers all parameters well, but the absence of an output schema increases the burden on the description to explain how results are returned. The description says the tool produces a narrative brief but does not state whether this is returned immediately or the caller must later poll check_research_status. That is a material operational gap for a research-launch tool and the exact reason siblings like that exist.

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%: every parameter (query, mode, depth, userId, graphId, sub_themes) has an explanatory description and constraints. The tool description itself adds one relevant pointer by implicitly warning to put detail in sub_themes rather than query, and by relating that the tool automatically includes context when warranted, but does not significantly explained beyond what the schema already covers. This is appropriately a baseline 3.

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 strong verb, 'Launch an autonomous Deep Research session,' and names the concrete resource it acts on: Fodda knowledge graph intelligence combined with live web research. It clearly states the deliverable ('comprehensive editorial-quality report' with inline citations) and differentiates itself from simpler lookups by stating that earnings and supplemental tools should not be called separately.

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 explicitly states when to use this tool: 'for complex, multi-faceted questions that need both curated expert intelligence AND current web context,' and provides concrete examples such as strategic briefings and competitive deep dives. It also advises against calling earnings or supplemental tools separately. It does not, however, name specific alternative sibling tools or provide explicit 'do not use when...' guidance for simple questions.

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