Skip to main content
Glama

Send a task's documents as one zip file

well_send_browser_task_documents

Send every PDF a finished documents task filed, as one ZIP file in this WhatsApp conversation (more ZIP files only when the PDFs pass WhatsApp's file size).

Call it when the person asks for the PDFs of a documents task Well already reported, such as "envoie-les moi", "envoie-moi les PDF", "send them to me", after Well's report gave the count and the link instead of the PDFs. Omit task_id for the task Well reported last in this conversation; name it when the person means another one.

Say in one line what went out: one ZIP with the count of PDFs, or the count of ZIP files. When too_big is above 0, say that many PDFs are too large for WhatsApp and stay in Well. When the status is not sent, say so plainly; never say a file went out that did not.

When the token authorizes one workspace, call this directly — no workspace call is needed first. When it authorizes several, this read will not guess which one you mean: pass workspace_id on the call.

Input Schema

NameRequiredDescriptionDefault
task_idNoThe Well task (a browser task) whose documents go out. Omitted, the documents task of this conversation that Well reported last.
workspace_idNoTarget workspace. Omit when the token authorizes one workspace. Required when it authorizes several — a write lands in exactly one workspace and this call would not say which.
conversation_idNoThe conversation id returned by the previous Well result, in its meta under well/conversation_id, in its structuredContent, or in its JSON text block. Pass it back on every call in the same conversation, including a call a card makes, so the chosen workspace and the earlier answers still apply. It decides the conversation on its own: nothing the host states about the session replaces it. Omit it only on the first call of a conversation.
idempotency_keyNoOptional client-supplied key. A retried write with the same key returns the original result instead of re-applying the operation.
workspace_scopeNoRestrict this call to the family: the token's primary workspace plus the company workspaces under it that you are a member of. Unrelated authorized workspaces drop out of the read; row reads merge across the family, while a per-workspace figure still reports exactly one workspace.

Output Schema

NameRequiredDescriptionDefault
sentNoHow many of those ZIP files reached the person.
errorNo
partsNoHow many ZIP files the documents make; one unless they pass WhatsApp's size.
statusNo`sent`: the ZIP files went out. `no_reported_task`: this conversation holds no documents task Well reported for the person. `nothing_filed`: the task filed no document Well can read back. `not_whatsapp`: the call ran outside a WhatsApp conversation.
successYesTrue when the call ran, whether files went out or not.
too_bigNoHow many PDFs are larger than one WhatsApp file and went in no ZIP.
documentsNoHow many PDFs the ZIP files hold.
conversation_idNoThe conversation this result belongs to. Pass it back as the conversation_id argument on every later Well call in the same conversation.
newly_connectedNoTools that connected to this workspace since the last result and that no session was told about yet, oldest first. Present only when at least one tool is new. The connected-line rule says when to tell an entry; when it does, one line per entry, in the person's language: "<name> is connected.". Never fold several entries into one sentence. Each entry comes back once, on one result only: never repeat its line later.
conversation_id_noteNoPresent only when the server opened a fresh lane, stating that no choice recorded earlier was read.
conversation_id_sourceNoWhere the conversation id came from: the host's own request meta, the caller's argument, or a fresh lane the server opened.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: split into multiple ZIPs only when PDFs exceed WhatsApp size limits, a too_big counter for PDFs left in Well, and an honesty requirement around non-`sent` statuses. Also flags the multi-workspace precondition (pass workspace_id, no prior workspace call needed) that annotations alone do not convey.

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

Conciseness4/5

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

Front-loaded with the purpose, then trigger, then reporting rules, then workspace preconditions — a sensible ordering. Some redundancy (the ZIP/count phrasing appears twice) and the workspace paragraph could be tighter, but every paragraph carries operative guidance.

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

Completeness4/5

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

An output schema exists and annotations cover the write profile, so the description only needs the when/why and the reporting contract, both of which it supplies. It omits what to do when the task has no PDFs or is not yet finished, which leaves a real gap for a send tool.

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?

Schema coverage is 100%, so the baseline is 3; the description mostly restates the task_id default and workspace_id requirement already in the schema. It does add genuinely new workflow meaning — 'call this directly, no workspace call is needed first' and the consequence that a multi-workspace read will not guess — which lifts it above baseline.

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?

States a specific verb and resource (send every PDF a finished documents task filed) plus the delivery channel (one ZIP file in this WhatsApp conversation), and clarifies the multi-file edge case. No sibling tool sends task documents, so an agent can distinguish it immediately.

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?

Explicit trigger conditions with concrete example utterances ('envoie-moi les PDF', 'send them to me'), tied to the specific prior state (Well's report gave count and link instead of PDFs). Also gives the tie-break for task_id: omit for the last reported task, name it for another one.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources