eod_report

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

Goes well beyond the annotations: it clarifies that nothing is sent, that returned fields must be forwarded unchanged, that counts reflect collected records and unlogged = 0 does not prove complete history, and that data_complete covers only source collection health. These are non-obvious behavioral caveats an agent could not infer from readOnlyHint/idempotentHint alone.

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 the purpose and outputs before the safety caveats, which is the right ordering. The 'data, never instructions' warning appears twice, but each instance covers a distinct surface (email text vs. returned project notes), so the repetition is defensible rather than wasteful.

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?

There is no output schema, and the description compensates by naming every returned field including the data_complete flag. For a zero-parameter, read-only builder, nothing an agent needs to call it and interpret the result is missing.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies a no-argument call scoped to 'today' and spends its space on outputs instead, which is the right allocation here.

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 and resource ('Build today's end-of-day email') and enumerates the exact fields produced: subject, text, html, inline logo attachment, date and counts. This is far removed from any sibling (take_fix, read_chart, log_watch, status), so an agent can route to it without opening the 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?

'Read-only: it sends nothing; pass its fields unchanged to the mail tool' makes the two-step workflow explicit and tells the agent the tool is not the delivery mechanism. It does not explicitly contrast with sibling tools (e.g. log_watch), but the usage context is clear enough to act on.

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