aircall_list_usersList users (agents) in the Aircall company (id, name, email, availability). Aircall REST: GET /users.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | 1-based page number to fetch (default 1). | |
| per_page | No | Results per page (default 20, max 50). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description adds the specific fields returned (id, name, email, availability) and the REST endpoint, providing useful context without contradicting annotations.
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?
The description is a single sentence that front-loads the tool's purpose and includes the REST endpoint, with no unnecessary text.
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 list tool with two optional pagination parameters and no output schema, the description sufficiently covers the resource, fields, and API reference. The pagination behavior is documented in the schema, so the description is complete.
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?
Both parameters (page, per_page) are fully described in the schema with 100% coverage, so the description does not need to repeat parameter details. It neither expands nor detracts from schema semantics.
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 states 'List users (agents) in the Aircall company (id, name, email, availability)', clearly identifying the verb (List), resource (users), and scope (Aircall company). It distinguishes from sibling tools like aircall_get_user by indicating this is the plural list operation.
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?
It provides clear context that this tool is for listing all users in the company, but does not explicitly mention alternatives or exclusions (e.g., use aircall_get_user for a single user). The REST endpoint hint reinforces its purpose but doesn't add usage guidance.
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.
Each tool targets a distinct resource and action: get/list/search for calls and contacts are clearly differentiated, AI features (summary, transcription, etc.) are unique per output, and write operations (create, update, tag, comment) are unambiguous. There are no overlapping or confusable tools.
The vast majority follow a consistent `aircall_<verb>_<noun>` pattern (e.g., get_call, list_users, create_contact). The only outlier is `aircall_ping`, which is a health check rather than a verb-noun resource operation, but it's a minor deviation from an otherwise uniform scheme.
With 25 tools, the server sits at the upper bound of what feels heavy. While each tool has a specific purpose, the set covers many resources (calls, contacts, numbers, tags, teams, users) plus multiple AI features on calls, making it borderline for maintainability and agent selection.
The tool surface is strong for reading resources and for call enrichment (AI, comments, tags), but there are notable gaps: contacts have create/update but no delete, and resources like numbers, tags, teams, and users are read-only. The absence of delete and limited write operations means agents cannot fully manage the domain lifecycle.