Get Research Summary

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The verbs 'Review' and 'Returns' imply a read-only operation with no side effects, which is accurate. However, it does not explicitly state that this is a non-destructive retrieval, nor does it disclose behavior when research is incomplete or when the session is invalid. The read-only nature is mostly left to the 'get_' naming convention rather than stated.

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 short, and the checkpoint directive is front-loaded. However, the '⭐ USER CHECKPOINT' formatting with emoji and all-caps is noisy for an agent parser and reads more like a human-facing UI label than a machine-readable directive. The two sentences are efficient but the first is workflow guidance that could be tightened.

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?

An output schema exists, so return format is covered elsewhere. For a tool sitting in a research workflow, the 'USER CHECKPOINT' line conveys its position as a review-before-proceeding step, which is useful. But it doesn't clarify the workflow sequence relative to siblings like research_topic or approve_research, or what 'proceeding' refers to specifically. Adequate but with gaps in workflow positioning.

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% — the single required parameter session_id is fully described in the schema ('Active session ID'). The description adds nothing about the parameter, but that's acceptable since the schema fully covers it. Baseline 3 applies as the schema does the heavy lifting and no additional semantic context is needed.

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 verb and resource: 'Returns detailed summary of all sources, images, themes, and credibility scores.' It distinguishes from siblings like get_full_draft (draft content) and get_session_status (session state). The 'USER CHECKPOINT' preface adds workflow framing but is not part of the purpose statement, keeping the core purpose clear.

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 'Review all research before proceeding' directive gives useful context that this tool is a checkpoint used before advancing in the workflow, and 'get_' naming implies it's for retrieving rather than mutating. However, it does not explicitly name when not to use it, nor does it reference siblings like research_topic, approve_research, or get_full_draft to disambiguate. The usage context is implied rather than explicit.

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