list_taskattachmentsList the files attached to a task (name, size, url) — e.g. customer context on a ticket. Files can also be attached over MCP with request_taskattachment_upload (a temporary-token upload, no base64 in the model's context). Each attachment carries app_url, a deep link to the drawer of the task it is attached to.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, covering safety. The description adds useful behavioral context: the returned fields (name, size, url) and that each attachment includes an app_url deep link to the task's drawer. This goes beyond the annotations and helps the agent anticipate output, though it does not mention pagination or ordering. Score 4 is appropriate because it complements rather than contradicts 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 three sentences, each informative: purpose, alternative upload method, and output detail (app_url). No wasted words, front-loaded with the core function. It is appropriately concise while covering essential aspects.
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 read-only list tool with one parameter and no output schema, the description is sufficiently complete. It specifies the output fields (name, size, url) and highlights the app_url deep link. It does not mention pagination or limits, but given the low complexity and the annotations, this is not a significant gap. A 4 reflects that it might need a small note on ordering or limits but is already solid.
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?
The single parameter task_id is explicitly described in the schema ('ID of the task the attachments belong to'), so schema coverage is effectively high (the signal says 0% but that likely refers to description coverage, not schema). The description does not add any additional parameter semantics, so the baseline of 3 applies: the schema carries the burden and the description adds nothing beyond 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?
The description clearly states the action: 'List the files attached to a task' with the specific returned fields (name, size, url). It distinguishes this from sibling tools like list_attachments (which likely lists all attachments) and retrieve_taskattachments (singular), and it provides an example use case. The verb 'list' and resource 'task attachments' are explicit.
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?
The description gives a concrete usage scenario ('e.g. customer context on a ticket') and mentions an alternative approach for attaching files via request_taskattachment_upload, which helps the agent decide when to use this tool for reading vs. writing. It does not explicitly state when not to use it or contrast with list_attachments or retrieve_taskattachments, but the guidance is sufficient for typical selection.
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.
Most tools are clearly scoped to a specific resource and action, but a few near-overlapping pairs (e.g., list_attachments vs list_taskattachments, create_tasktags vs add_tag_tasks) could cause misselection without close reading. Descriptions are detailed enough to resolve most ambiguity.
The dominant verb_noun CRUD pattern (create_, list_, retrieve_, update_, partial_update_, destroy_) is consistent and predictable. However, non-standard pluralizations (companys, resumeentrys, taskdependencys) and a handful of irregular names (task_assign_user, move_relate_to_tasks) introduce minor inconsistencies.
With 83 tools, this server is far beyond a well-scoped MCP surface, even for a feature-complete project management suite. The sheer volume will overwhelm agents and make selection inefficient, clearly falling into the extreme-mismatch range.
The toolset provides thorough lifecycle coverage across companies, projects, tasks, sprints, attachments, comments, dependencies, tags, reminders, resume entries, tickets, and users. Missing operations like company deletion or task-attachment creation appear intentional and are worked around via existing tools.