Upload base64-encoded files to a Targetprocess card, then read them back to confirm the attachments arrived.
Upload files to a card (UploadFile.ashx). Each file is given as base64 content with a name; pounce never reads local files itself, so the client decides what may be uploaded. Attachments are read back to confirm they arrived.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| files | Yes |
Changes observed during successful MCP inspections.
v1.0.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false and destructiveHint=true, which the description does not contradict. It adds genuinely useful behavior beyond annotations: pounce never reads local files itself (so the client decides what may be uploaded) and attachments are read back to confirm arrival. It doesn't clarify what the destructive aspect means (e.g., overwriting existing attachments), but the annotations already carry that flag.
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 sentences, purpose front-loaded in the first. The endpoint reference, the client-side content disclosure, and the read-back confirmation each add distinct value. The middle sentence is slightly wordy but packed with meaning; nothing is wasted.
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 two-parameter upload tool, the description covers the essential call semantics and even hints at success verification via read-back. But there is no output schema, and the description doesn't specify what a successful call returns, how failures surface, or whether uploading replaces existing attachments — which matters given destructiveHint=true.
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?
Schema description coverage is 0%, so the description must compensate. It explains the core semantic of the files parameter (base64 content plus a name), which aligns with contentBase64 and name in the schema. However, it never explicitly states that id is the card identifier, and mimeType is left entirely undocumented, so compensation is only partial.
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 opens with 'Upload files to a card', a specific verb plus resource, and anchors it to the concrete endpoint (UploadFile.ashx). This clearly separates it from read_attachments (reading) and from other write_* siblings that create or update cards rather than attaching files.
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 usage context is inferable from the action (attaching files to a card), and the read-back note hints at the verification workflow, but no explicit alternatives, exclusions, or when-to-use conditions are stated. An agent must guess that read_attachments is the counterpart for retrieval.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.