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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description earns credit for adding new context: a bounded recency window, zero cost, account/connection visibility scoping, and an explicit statement of what is excluded (no source text, no new calculation). It does not explain the bound's size or pagination behavior.

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 with the verb and resource first, followed by a compact cost/boundary clause. Dense but nearly waste-free; the trailing fragment after the semicolon is slightly clipped but still informative.

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?

With no parameters, an output schema present, and rich annotations, the description only needs to convey scope, cost, and boundaries – all of which it does. The 'bounded' window size is left undefined, which is the one minor 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?

The tool takes no parameters, so the baseline is 4; there is nothing for the description to clarify beyond the schema. It correctly adds no redundant parameter prose.

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?

Names a specific verb (Read) and resource (bounded recent research-operation metadata) and enumerates the payload fields: request IDs, states, recorded credits. This clearly separates it from siblings like get_research_status, get_research_balance, and recover_research_result. It stops short of explicitly naming which sibling it displaces.

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?

Usage is implied rather than stated: 'no source text or new calculation' hints that read_evidence or measure_evidence serve those needs, and 'Free' signals it is cheap to call. There is no explicit when-to-use or when-not-to-use routing against the many adjacent research siblings.

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