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

With no annotations, the description carries the full burden and delivers real behavioral detail: authentication ("No key needed"), rate limiting ("limited per address"), pricing ("Free"), and specific error semantics (404 page_not_found vs 422 malformed). It also explains edge-case return semantics like reproduced being null "for too few". Missing only concrete rate-limit numbers 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?

It is front-loaded with the content of the page, but the description is a dense run-on enumerating many output fields (n per run and per cell, shown_a/shown_b, reproduced, direction) when an output schema already exists to define them. Several clauses restate return shape rather than earn their place; error codes and access notes are the highest-value content.

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 single-param lookup with 100% schema coverage and an output schema, the description covers auth, rate limiting, and error handling thoroughly, which is what an agent most needs. The main gap is sibling differentiation (list_research, get_find), so an agent knows what it gets but not fully why this tool over alternatives.

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 coverage is 100% and the slug parameter already documents its valid values (openings, title-devices, title-thumbnail-overlap). The description's additional field detail (n per cell, shown_a/shown_b, reproduced) describes response fields, not the input parameter, and provides no extra meaning about what slug should be. Baseline 3 applies.

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 specific verb+resource ("One research page") and enumerates what it returns (per-run numbers, n per cell, reproduced status, direction, measures). It's clearly a single-item detail fetch. However, it never distinguishes itself from sibling tools like list_research or get_find, and the trailing "Same as GET /v1/findings/{slug}" muddies rather than clarifies the relationship to get_find.

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 only implied: the required slug plus "404 for unknown slug" signals you need a known identifier, which suggests fetching detail for an item you've already listed. There's no explicit when-to-use vs list_research, and no alternative routing. Incremental guidance like "no key needed, limited per address" is present but is about access, not tool selection.

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