local_data_report

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

Goes well beyond the annotations: it discloses that unreadable folders are reported as incomplete (incomplete_reason, folders_that_could_not_be_listed) and never as empty, defines the non-overlapping not_settled_* states, and warns never to suggest deleting the journal/skips file. It also discloses the per-call receipt-line side effect and that nothing is written to Tally, which is exactly the kind of context readOnlyHint alone cannot convey.

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 and information-dense, but delivered as a single sprawling paragraph riddled with nested parentheses ('not_settled_binding_refused: native posts whose binding... including one Tally rejected in part or whole') that make it hard to scan. Almost every clause carries real meaning, but the packaging costs the reader.

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 zero-parameter, no-output-schema tool this is unusually complete: it enumerates the returned fields (counts, sizes, age, journal state), defines each status value, states coverage boundaries, and describes the partial-evidence failure mode. An agent has everything needed to call it and interpret the result.

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 per the rubric the baseline is 4; there is no parameter syntax the description could add. The description instead spends its budget on the semantics of the returned fields, 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?

Opens with a specific verb and resource: 'Reports what ComplyEaze Bridge stores locally, by class, with counts, sizes, the age of the oldest file and the state of its import journal.' It is instantly distinguishable from the Tally-data siblings (balance_sheet, vouchers, trial_balance) because it inspects Bridge's own local folders and dispatch-lock folder rather than book content.

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 draws explicit scope boundaries: what is covered (the folder the MCP server and desktop Journal flow share) versus what is not (the desktop app's other settings, mirror database and logs). It also frames correct interpretation ('never treat it as proof that a batch is absent'). What is missing is naming a sibling to use instead when the agent actually wants Tally-side evidence, which is why it falls short of 5.

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