MintMCP Docs

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

Annotations already declare readOnly, idempotent, and closed-world, so safety is covered; the description adds that the return is full markdown content rather than a snippet, which is useful behavioral context. It stops short of noting any truncation limits or page-size behavior, keeping it from a 5.

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?

Three sentences, front-loaded with the core action and followed by usage and the alternative route, with no redundant phrasing. Every sentence carries a distinct instruction.

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?

Single documented parameter, rich annotations, and an output schema mean the description need not explain return values; what remains, provenance and routing to get_page, is fully covered.

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 only parameter's description already says 'document id returned by search or list_docs,' so the description's provenance hint repeats structured data. Baseline 3 is appropriate; no extra format or length constraints are added.

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?

States a specific verb and resource (fetch full markdown content of a Mintive documentation page) scoped to lookup by id. It explicitly distinguishes itself from the get_page sibling, which is keyed on URL/slug rather than a search-result id.

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?

Gives explicit sequencing ('use it after search (or list_docs) to read a page in full before answering') and names the alternative with the condition that selects it: if you have a URL or slug, use get_page instead. Nothing is left to inference.

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

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

Annotations already declare readOnly, idempotent and closed-world, so safety is covered. The description adds real value beyond that by stating the return payload is full markdown identical to fetch, which tells the agent not to chain calls for the raw text. It does not disclose failure behavior for malformed slugs or truncated pages, which keeps it below 5.

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?

Three short sentences: what it fetches, when to use it, what it returns. Front-loaded with the action and scope, and every sentence carries distinct information with no repetition of the schema.

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 annotations covering side effects, a 100%-covered single parameter, an output schema handling return values, and a clear usage trigger, the definition is essentially complete. The only residual ambiguity is why one would choose this over fetch given the identical payload, which is left for the agent to resolve.

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?

There is one parameter at 100% schema description coverage, and the schema example ('enterprise/sso') mirrors what the description shows. The description reinforces dual URL-or-slug acceptance but adds no format rules, normalization behavior, or validation notes beyond the schema, so the 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?

States a specific verb and resource ('Fetch a Mintive documentation page') and immediately constrains scope to public docs URLs or slugs, with two concrete examples. An agent can tell this is the docs-page reader rather than a generic web fetcher or a search tool.

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?

Gives a clear trigger ('when a user pastes a docs link or names a page directly'), which routes the agent well. It stops short of an explicit exclusion — e.g. 'use search when the user describes a topic rather than naming a page' — so the boundary with search and list_docs remains inferred.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds useful non-annotation context: the output is a TOC grouped by category, entries carry page ids consumable by `fetch`, and the category filter narrows the listing. It doesn't mention pagination or size limits, keeping it below a 5.

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?

Three sentences, front-loaded with what the tool returns, then usage, then the optional filter. The final sentence mildly echoes the earlier 'grouped by category' phrasing, a small redundancy that keeps it from a 5.

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 values needn't be detailed, yet the description still conveys the essential shape (category groups containing page ids) and how to act on them. For a single-optional-parameter browse tool with read-only annotations, nothing an agent needs is missing.

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%, so the baseline is 3, but the description adds meaning by framing `category` as a narrowing filter over the grouped listing and reiterating real category names that appear in the grouping. This connects the parameter to the output structure rather than just restating it.

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?

States a specific verb and resource (list the Mintive documentation table of contents) and adds the organizing structure (grouped by category). It also explicitly links the output to the sibling `fetch` tool by noting each entry has a page id, which lets an agent separate this browse step from the read step.

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?

Gives clear when-to-use context: 'to see what the docs cover or to browse a category before reading a page,' which implies this precedes `fetch`/`get_page`. It does not explicitly name when to prefer `search` or `get_page` instead, so it stops short of full alternative routing.

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

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

Annotations already declare readOnly, idempotent, and closed-world, so the safety profile is covered without prose. The description adds genuine context beyond that: what fields come back, that coverage spans architecture and per-connector guides, and that ids are the handoff key to fetch. It omits result-count limits or pagination, which keeps it short of a 5.

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?

Three sentences, front-loaded with purpose and return shape before the usage rule and the follow-up handoff. The connector/feature list is dense but directly aids query formulation, so every clause earns its place.

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?

The tool has one required parameter, full schema coverage, annotations, and an output schema, so the description need not explain returns or safety. Given that low complexity, purpose, entry point, and next step are all present and nothing an agent needs to call it correctly is missing.

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% and the schema's own query description already supplies five concrete examples plus a 16000 max length. The tool description adds only the general framing that queries can span connectors and features, which is marginal value over structured data. Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb and resource ("Search the full Mintive documentation") and immediately names the return shape (ids, titles, URLs). It also distinguishes itself from the fetch sibling by explaining that the ids it returns feed that tool, so an agent can tell the two apart without opening a schema.

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?

"Use this first for any Mintive question" is an explicit precedence rule over the siblings, and the enumerated topic areas (setup, capabilities, security, connectors, SCIM, SIEM) define the triggering scope. The follow-up step ("pass a result id to the fetch tool to read the page") gives the agent the exact routing sequence to the alternative.

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