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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-obvious behavior on top: mixed income/expense categories net out as income minus expenses, output is in the user's display currency, details are ordered largest first, and undescribed records collapse into one entry flagged isUngrouped. These are computation and shape traits an agent could not derive from the schema 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?

Two sentences, front-loaded with the primary output and followed by the two conditional behaviors, with no filler. It is dense but every clause carries information; slight length is justified by the aggregation rules it must convey.

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?

With annotations, full schema coverage, and an output schema present, the description needs only to cover behavior not captured structurally, and it largely does. Minor gaps remain, such as whether all 12 months are always returned (and as zero when empty) and what a report with no matching categories yields.

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 baseline is 3, but the description adds real meaning the schema lacks: it explains the netting semantics applied when `type` is omitted and exactly what includeDetails produces (per-category and per-label grouping, ordering, isUngrouped flag). Only `year` and `id` are left entirely to the schema, which is appropriate.

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 names a specific verb and resource ('Returns a trend report's totals for each month') and pins down scope (per month, one year, display currency), which is far more precise than the title. It does not explicitly contrast itself with list_trend_reports or get_spending_summary, so an agent must infer the split, keeping it just under a 5.

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?

Usage is implied rather than stated: the agent can infer this tool is for aggregated monthly trend data, but there is no explicit 'use this when / not when' or named alternative such as get_spending_summary. The includeDetails clause gives conditional behavior, not selection guidance.

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