dosare_files_upload

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the bar is lower. The description still adds non-obvious behavior: accepted formats (PDF/JPG/PNG/TIFF), a 10 MB size cap, and the downstream effect that uploaded files become the zip attachment of the C168 filed from the dosar — all information an agent cannot get from annotations.

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, front-loaded with the purpose and document-kind mapping, then constraints, then downstream effect. Slightly list-heavy in the kind enumeration, but every clause carries information an agent needs.

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 4-parameter mutating tool with no output schema, the description covers purpose, valid kinds, file constraints and the consequence of uploading. What remains unaddressed is permission/auth requirements and duplicate-handling, which are secondary for a non-destructive, non-idempotent upload.

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 coverage is 75%, so the schema already documents id, path and companyId. The description adds meaning the schema lacks: the semantic intent of each `kind` enum value and the constraints on the file at `path` (formats and 10 MB limit). companyId's override behavior is left entirely to the schema, which is acceptable at this 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?

States a specific verb and resource ('put a file into a dosar') and immediately disambiguates the resource further by mapping each `kind` value to a concrete document type. An agent can tell this is the write-side companion of dosare_files_download without opening the schema.

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 kind-to-document mapping implicitly guides which value to pass, which is real usage help. However, it never says when to use this tool instead of the sibling dosare_attach, nor any preconditions (does the dosar need to exist, are duplicates rejected?). Use is implied rather than stated.

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