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

Annotations declare a non-read-only, non-destructive, non-idempotent write; the description adds real context beyond that — the refusal behavior for unfinished runs, the 100-character label cap and the fallback naming scheme, and the two return fields (report_url, where). It does not say what happens if the same task is saved twice, which matters given idempotentHint=false, so it is not a 5.

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?

Purpose is front-loaded in the first sentence, and the bulleted run-type list earns its space by telling the agent what shapes of result are valid. The closing sentence about `where` restates the location a second time and is mildly redundant.

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?

With no output schema, the description compensates by naming report_url and where and explaining why both exist. Combined with the completion precondition and default-naming rule, an agent has everything needed to invoke this correctly against a 2-parameter mutation.

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 0%, so the description carries the full burden and does so well: task_id is tied to a prior start_* call, and label is described as optional, capped at 100 characters (a constraint absent from the schema), with the default naming convention spelled out. Minor gap: no format expectation for task_id.

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?

A concrete verb plus resource: it saves a finished run's result into the user's Research Library, and it enumerates exactly what a saved run contains (figures, trades, equity line for a backtest; passing names for a scan). It distinguishes itself from the start_*/get_*_progress siblings by being the terminal persistence step, but it never names a sibling alternative, so it stops short of a 5.

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?

It gives a clear precondition and a negative case: the run must be finished, and saving a running task is refused with a message telling the user to wait. That is genuine when-to-use/when-not guidance, but there is no explicit routing to or away from any named sibling tool.

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