get_submissionUse to read one stored submission by id, including file metadata and files_url (the form inbox). Do not use this for live submit tests — POST to /s/:publicKey instead. Do not expect signed bucket URLs — download from the inbox.
| Name | Required | Description | Default |
|---|---|---|---|
| submission_id | Yes | Submission id from list_submissions or a webhook payload. |
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?
With readOnlyHint and idempotentHint already present, the description adds valuable behavioral context beyond annotations: it clarifies the response includes files_url and that URLs should not be expected to be signed bucket URLs. This prevents a common failure mode.
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?
Three short sentences deliver purpose, exclusions, and a critical caveat without any filler. The main intent is front-loaded and each sentence earns its place.
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 one-parameter read operation with safety annotations, the description provides enough context to invoke the tool correctly and understand the return characteristics. No output schema is needed because the description states the important return components.
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 input schema fully documents submission_id, including format, pattern, and source. The description does not need to add much parameter detail, so the baseline of 3 applies given 100% schema coverage.
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 tool reads one stored submission by id and specifies what it includes (file metadata and files_url). This distinguishes it from list_submissions and from the live submit endpoint.
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 explicitly says not to use this for live submit tests and directs the agent to POST to /s/:publicKey instead. It also provides guidance on how to handle returned URLs by downloading from the inbox.
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 separated by resource and action (get_client vs list_clients vs create_client), and the descriptions explicitly warn against misuse. However, update_account and update_team both cover renaming a workspace/team, and get_account and get_project both return plan/usage/branding, creating a couple of genuinely confusing boundaries.
The set overwhelmingly follows the snake_case verb_noun pattern: archive_client, create_form, get_submission, list_projects, rotate_project_inbox, test_webhook, etc. Minor deviations exist: bootstrap_site uses 'site' instead of 'project', update_team vs update_account introduces noun inconsistency, and upsert_project_webhook uses a different verb than the update_* family.
With 27 tools, the server exceeds the 25-tool threshold that signals a too-large surface for an MCP server. While the broad scope (clients, projects, forms, submissions, teams, billing, webhooks) explains the count, there are redundant near-duplicates like update_account/update_team and bootstrap_site overlapping with multiple create tools, making the set feel bloated rather than curated.
The lifecycle coverage for clients, projects, and forms is solid with create, read, list, update, and archive operations. However, there is no unarchive (explicitly noted as unavailable), no submission management beyond read (no delete/export/update), and no webhook delivery history, leaving notable dead ends and gaps in the core workflow.