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

Beyond the readOnly and destructive annotations, the description discloses that figures are decimal-string rupees, that Books plus spreading equals MIS, that cost and profit reconciliations are independent views, and that known_stale/not_assessed flags disclose run state. It also explains page_token is signed and source-pinned, adding non-obvious 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?

The description is dense but front-loaded, placing the management data class and read action first. Every sentence carries load-bearing information: currency format, reconciliation relationship, filtering, pagination, and run-state flags, with no 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 tool with no output schema, the description conveys what an agent needs to call and interpret the result: data class, partition choice, relationship between figures, pagination behavior, and run-state disclosure. It does not spell out the exact response shape, but the provided semantics are sufficient for correct invocation.

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%, so the baseline is 3, but the description adds meaning by explaining allocation_dimension is an exclusive cost/profit partition and elaborating on page_token with the source-pinned restart rule. It reinforces min_abs_mis and account_name_patterns as filtering-before-paging behaviors, though it does not enumerate every parameter since the schema already does.

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 states a specific verb ('Read'), resource ('allocation account figures'), and exact scope: one explicit cost or profit partition of the current persisted allocation run at account grain. It also distinguishes the two independent reconciliation views and warns not to add them, separating it from related allocation tools.

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 provides clear usage context: MANAGEMENT data class, cost vs profit partition, filtering before paging, and the source-pinned page_token caveat. It does not explicitly name sibling alternatives such as get_allocation_target_figures, so it falls short of a full when/when-not comparison.

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