get_evidenceFor one category (and optionally one product id): each criterion, its weight, and per product the score with the quoted passage, its source URL and the day it was read.
| Name | Required | Description | Default |
|---|---|---|---|
| product | No | A product id from get_ranking (optional). | |
| category | Yes | A category id from list_categories, e.g. "exchange" or "hardware_wallet". |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real value by enumerating the returned content (per-criterion weights, quoted passages, source URLs, retrieval dates), which matters because no output schema exists.
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 dense sentence with no filler, front-loading the scope (one category, optionally one product) before the returned fields. The phrasing 'the day it was read' and the compressed list of outputs read slightly awkwardly but stay economical.
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 output schema, the description does the necessary work of describing the return shape, and it covers both parameters' roles. It is silent on volume (how many criteria/products come back) and any pagination, which is a minor remaining gap for a two-parameter read tool.
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 both parameters are already documented with their source of valid ids, so the baseline is 3. The description contributes only the confirmation that the product filter is optional and narrows the per-product detail rather than the category itself.
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 names the resource precisely (per criterion: weight, score, quoted passage, source URL, read date) scoped to one category and optionally one product, which is clearly distinct from get_ranking's aggregate view. It never states the verb outright (implied by the 'Get' title) and does not name siblings, so it stops short of a 5.
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 agent can infer this is the drill-down behind a category's scores, and the schema hints that ids come from list_categories and get_ranking. There is no explicit when-to-use, when-not-to-use, or alternative-naming guidance in the description itself.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.