llm_digest

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

No annotations provided, so description carries the burden. It discloses the digest content (summary, spikes, simulation) and webhook option. However, it omits details like whether the webhook send is destructive or reversible, and does not mention rate limits or access restrictions.

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 description is relatively concise, with only three sentences plus an Args listing. The structure separates purpose from details, but the Args section repeats schema defaults. Could be more concise by integrating into prose.

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 simple two-parameter tool with an output schema, the description covers the main use case and both parameters. It lacks detail on the output format (though output schema exists) and edge cases, but is adequate for typical usage.

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 description coverage is 0%, so description must compensate. It explains period with explicit valid values (today, week, month, all time) and send with its effect (POSTs to webhook if true). This adds meaningful context beyond the bare schema types.

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 clearly states it generates a savings digest and optionally sends it to a webhook. It specifies the contents (summary for a period, spend spikes, simulation) which distinguishes it from sibling tools like llm_budget or llm_savings.

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?

No guidance on when to use this tool versus alternatives. The description does not mention conditions like 'use when you need a digest' or exclude cases where other tools might be better (e.g., for raw data use llm_query).

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