partial_task

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

With no annotations, the description carries the full burden and does so: it forbids embedding secrets, defines the exact retry ordering relative to credential attempts, discloses multi-agent scoping and the TAB_NOT_OWNED rejection, and states a configurable cap (default 8, 1-64). That is substantial behavioral context beyond the schema.

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?

Front-loaded with purpose and the alternative tool, and nearly every sentence adds a rule. Slight redundancy in listing the five auth/manual blocker examples already present as a schema enum, and the paragraph is dense, but nothing is padding.

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 6-parameter, annotation-free mutation of task state, the description covers blockers, secret hygiene, retry ordering, tab/session scoping, and caps. It stops short of stating what happens to the task/session after the call (terminated vs. resumable), which is the one remaining behavior an agent would want.

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%, so the baseline is 3, but the description adds conditional usage rules the schema lacks: when tab_id is warranted (multiple tabs/sessions) and when session_token applies (only finalizing a client-owned visual session). It also specifies the three content elements to preserve in the payload.

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+resource outcome: signaling partial completion when useful work is done but an external blocker stops the final step. It explicitly contrasts itself with fail_task, so an agent can distinguish the two without opening either 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?

Gives an explicit when-to-use rule ('use this instead of fail_task when the user can still benefit from the completed work'), enumerates the blocker classes that qualify, and adds a sequencing rule to let a single saved-credential/operator-prompt attempt happen first. Both the selection condition and the exclusion are stated.

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