ProWoDo

Read an attachment's text

read_attachments

Read-onlyIdempotent

Read the text content of an attachment — markdown (.md) first and foremost, plus plain text, CSV, JSON, YAML, XML and HTML. Use this after list_attachments or retrieve_attachments: the url those return is a short-lived signed URL on a private bucket and cannot be fetched directly. Pass the attachment id in kwargs and company_id in the body. At most 256 KB are returned per call: when truncated is true, call again with offset set to the returned next_offset to get the next slice, and repeat until truncated is false — size in the response is metadata written at upload time, not a count of bytes actually read, so don't rely on it to decide you are done paging. PDF and Office files (.docx, .xlsx, .pptx) are NOT readable yet — that is a known gap, not a broken file; point the user at app_url instead. Each attachment carries app_url, a deep link to its project's attachments page — null for company-level attachments, which have no dedicated page.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`body`	Yes
`kwargs`	Yes

TDQS

A5/5.0

Behavior5/5

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

Goes far beyond the readOnly/destructive annotations by detailing the 256 KB return limit, pagination via truncated and next_offset, the misleading nature of 'size' metadata, unreadable file types, and app_url behavior for company-level attachments. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence adds necessary information—usage sequence, pagination mechanics, known limitations, and fallback. It is well-organized and front-loaded with the core purpose, making it valuable despite its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and limited annotations, the description covers all critical context: how to invoke, how to page, what to warn users about, and where to redirect for unsupported formats. It is fully self-sufficient for an agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite schema description coverage at 0%, the description thoroughly explains the purpose of each parameter: attachment id in kwargs, company_id in body, and offset for paging. It also explains how to use the response's next_offset to continue reading, adding meaning not present in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Read the text content of an attachment'. It also distinguishes itself from list_attachments and retrieve_attachments by explaining that their returned URL is a short-lived signed URL that cannot be fetched directly, clarifying this tool's unique role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use this tool ('Use this after list_attachments or retrieve_attachments'), what to pass (attachment id in kwargs, company_id in body), and provides an explicit alternative for unsupported file types ('point the user at app_url instead'). This covers both use and non-use cases.

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

All ProWoDo tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0

Disambiguation4/5

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.

Naming Consistency4/5

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.

Tool Count1/5

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.

Completeness5/5

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.

Resources

Need Help?