Done Bear

Attach File to Task

task_attach

Attach a file to a task by fetching it from an HTTPS URL: the server downloads it, verifies its size and type, and stores it. The model never sends file bytes directly. Pass a stable idempotency_key and reuse it for retries so a lost response cannot upload the file twice. Limited to 10 attachments per task and 10 MB per file. Allowed types: images (jpeg, png, gif, webp, heic), PDF, CSV, Markdown, and plain text.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	HTTPS URL of the file to attach
`task`	Yes	Workspace-scoped task number, encoded as a string
`context`	Yes	Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."
`filename`	No	Display filename; defaults to the URL's last path segment
`workspace`	No	Workspace id, slug, or name
`idempotency_key`	No	Stable key that makes retries safe: repeated calls with the same key create only one record and return the same id.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	Yes
`taskId`	Yes
`attachment`	Yes

TDQS

A4.7/5.0

Behavior5/5

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

Beyond annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses concrete behaviors: server-side download and validation, the idempotency retry guarantee, the 10-attachment and 10 MB limits, and allowed file types. This gives the agent actionable expectations without contradicting any annotation.

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?

Four dense sentences, each earning its place: mechanism, retry guidance, rate/size limits, and allowed types. The core action is front-loaded, and no content is redundant with the schema.

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?

For a mutation tool with a 100%-described schema and an output schema present, the description covers the non-obvious behavioral details: the fact that the model never sends raw bytes, the idempotency contract, and hard limits. An agent has everything needed to invoke it correctly.

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

Parameters4/5

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

The schema already documents all parameters, so the baseline is 3; the description adds valuable extra meaning for idempotency_key (retry-safe single creation) and url (HTTPS, accepted types, size verification). Other parameters like task and context rely on the schema, but the added semantics for the trickiest parameters justify a 4.

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 ('Attach a file to a task') and explains the mechanism (fetching from an HTTPS URL), which clearly distinguishes it from sibling attachment tools like task_attachment_list and task_attachment_remove. The title and description align without tautology.

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

Usage Guidelines4/5

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

It gives clear operational context: server downloads the file, model must not send bytes, retries should reuse idempotency_key, and size/type limits. It does not explicitly name alternatives or state when not to use this tool, but the read-only sibling tools are semantically distinct, so the context is sufficient.

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

All Done Bear 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

Tools are grouped cleanly by resource (task, checklist, comment, label, project, attachment), so most actions have an obvious owner. The main ambiguities are task_list vs. search and checklist_done vs. checklist_edit, but the descriptions call out the intended boundaries clearly enough to avoid frequent misselection.

Naming Consistency4/5

The dominant resource_verb pattern (task_add, task_edit, checklist_list, comment_remove, project_join) is consistent and predictable. A few outliers like get_context, guide, search, and task_attachment_list break the pattern, but the naming remains readable and mostly uniform.

Tool Count2/5

At 35 tools, this is a very large surface for an agent to choose from and exceeds the 25-tool threshold where count becomes a liability. The tools are well organized, but the repeated verb families across six resources make the total feel heavy even though each tool is plausibly justified.

Completeness4/5

The core task lifecycle is well covered: create, show, edit, list, complete, reopen, archive, assign, and bulk operations, plus full checklist, comment, label, and attachment workflows. Notable gaps are the lack of an explicit unarchive/restore path and no label edit/delete, but these are minor enough that agents can usually work around them.

Resources

Need Help?