search

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

Beyond the readOnlyHint/idempotentHint annotations, it discloses sandbox execution, the exact shape of the spec variable, the absence of live YNAB API access, and the return shape (same CodeModeResult as execute). This is rich, non-redundant behavioral context.

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, environment, data shape, example, and caveat are all conveyed in a compact, front-loaded description. No sentence is filler.

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 single-parameter tool with no output schema, the description provides the spec keys, sandbox boundary, no-live-access disclaimer, and return shape reference. It is slightly dependent on the agent knowing what CodeModeResult looks like, but that is a minor gap given the example and sibling context.

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?

With 0% schema description coverage, the description largely compensates: 'code' is implied to be the Python snippet, and the example clarifies the expected form. It could be more explicit that the code must be a return expression and what happens on invalid input, but it is sufficient for correct use.

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 ('Discover') and resource ('available YNAB tools') by running a Python snippet against the tool catalog. It clearly separates this from live API operations by noting 'No live YNAB API access' and references execute only for return-shape comparison.

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 description makes the use case explicit: introspect/filter the tool catalog. It also gives an exclusion ('No live YNAB API access') and an example of how to query the spec. It does not explicitly enumerate when-not-to-use relative to siblings like execute or ping, so not a 5.

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