Capture an item

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

With no annotations, the description carries the behavioral burden. It discloses that capture auto-classifies, auto-assigns projects, checks for existing duplicates, and files the item, and that text is stored verbatim and never rewritten. It stops short of explaining what happens on duplicate detection or where the item is filed, but these are not essential for invocation.

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?

The definition is well organized: purpose, batching rule, autonomous behavior, and agent instructions in four sentences. It is efficient, though 'call it once per distinct item' and 'paste a transcript one item at a time' are slightly 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?

For a two-string-parameter tool with no annotations or output schema, the description is unusually complete: it specifies what to send, how often, what the tool decides, and what the agent should not do. The only minor gap is the absence of any return-value or confirmation behavior, but that is not needed to invoke the tool correctly.

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 already documents text and source. The description adds a useful constraint not in the schema: the text parameter must carry one distinct item at a time, not a batch. The verbatim/stored-exactly point repeats the schema, but the batching rule is genuine added meaning.

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 uses a specific verb and resource ('Save something the user wants kept: a note, a link, an email...') and clarifies that capture is the catch-all intake tool. It also distinguishes itself from siblings by stating it decides project, attention, and duplicates itself, so an agent won't confuse it with add_project or mark_done.

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 concrete usage rules: call once per distinct item, paste a transcript one item at a time, and do not classify or ask which project. It does not explicitly name sibling tools as alternatives, but the 'decides for itself' statement effectively routes the agent away from add_project and mark_done.

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