get_guideRead approved steps and the canonical FINLY guide link. A bank guide is not a recommendation.
| Name | Required | Description | Default |
|---|---|---|---|
| locale | Yes | ||
| guide_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| tool | Yes | ||
| as_of | Yes | ||
| result | No | ||
| status | Yes | ||
| receipt | Yes | ||
| evidence | No | ||
| no_action | No | ||
| request_id | Yes | ||
| assumptions | Yes | ||
| limitations | Yes | ||
| next_actions | Yes | ||
| response_kind | Yes | ||
| schema_version | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations already declaring readOnlyHint, idempotentHint, and destructiveHint false, the description still adds useful non-obvious context: the content is 'approved,' includes a 'canonical' link, and is explicitly not a recommendation. This helps the agent interpret the result appropriately beyond the schema or annotation metadata.
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?
Two concise sentences with the primary action front-loaded. The second sentence is a meaningful caveat rather than filler, and no words are wasted.
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 simple read-only tool with only two constrained parameters, a rich annotation set, and an output schema present, the description covers the essential purpose and an important interpretative caveat. It falls just short of perfect because the guide_id and locale semantics are left entirely to the schema.
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 0%, and the description does not mention either parameter. The agent is left to infer the meaning of locale and guide_id from names and schema constraints alone. The description must compensate for the missing parameter documentation, but it does not do so.
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 clearly identifies the tool's action ('Read approved steps and the canonical FINLY guide link') and its resource (approved guide). The phrase 'A bank guide is not a recommendation' adds a clarifying scope note, but it does not explicitly differentiate the tool from sibling tools such as get_claim or search_public_knowledge.
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?
No explicit guidance is given for when to use this tool versus the sibling alternatives. The description states what the tool does but does not provide context such as 'use this instead of search_public_knowledge when you need an approved guide' or any exclusion conditions. The final sentence is a clarification, not usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.