upload_status

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

With no annotations supplied, the description carries the full burden. It implies a read-only diagnostic but never says so, never states whether calling it clears or consumes the armed state, and never describes the response shape beyond a vague enumeration of counters. The one genuinely useful disclosure is the definition of 'foreign' as coming from another tab, but 'swallowed' remains opaque.

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?

It is a single front-loaded sentence with no filler, which is appropriate for a status query. But the compression is achieved through dense internal jargon and stacked parentheticals, trading clarity for brevity.

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?

There is no output schema, so the description is the only place the return values could be explained, and it only gestures at them ('whether filled', 'how many swallowed', 'how many foreign') without giving field names or types. For a diagnostic tool whose whole value is its returned status, this leaves the agent unable to interpret the result.

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 100% and all three parameters (lease, wait_s, session) are documented in the schema itself, including the multi-agent collision advice for session. The description adds no parameter meaning beyond that, so the baseline 3 applies.

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 names the resource (the armed file chooser) and the three things it reports: whether it was filled/consumed, how many were 'swallowed', and how many were 'foreign'. However, it never uses a plain verb like 'reports' or 'returns' and leans on undefined jargon ('armed', 'swallowed', 'no arm left'), so an agent must already understand the upload flow from sibling tools to know what this returns.

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?

There is no when-to-use guidance at all: nothing says to call this after upload_next, before upload, or instead of candidates/upload. The parenthetical 'no arm left' and 'from another tab while armed' hint at diagnostic scenarios but never state a trigger condition or an alternative tool.

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