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

Annotations only declare readOnlyHint=true and destructiveHint=false. The description significantly expands on this with deep behavioral details: null semantics ('null actual or variance means unavailable, never zero'), rollup behavior ('whole-report unfiltered rollups and no cross-side grand total'), privacy filtering ('withholds internal notes and may redact structured PII'), and pagination semantics ('source-pinned, so restart at page 1 if source_changed'). This goes far beyond the annotations and is highly informative.

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 a dense, well-structured paragraph that front-loads the core purpose ('MANAGEMENT data class. Read the existing budget-or-prior variance report') and then packs high-value edge-case details into a compact series of clauses. Every sentence contributes distinct information (nulls, rollups, explanations view, paging) without redundancy or 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?

This is a complex tool with 8 parameters, two views, pagination, and subtle data semantics, and there is no output schema. The description covers critical operational details: null handling, rollup behavior, explanation-view redaction, and paging restart logic. It is thorough enough that an agent could invoke this tool correctly with minimal additional inference, making it effectively complete for its complexity.

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 each parameter has a baseline description. However, the tool description adds meaningful semantics about how parameters interact: filters affect rows and filtered grain counts, and page_token is source-pinned. This goes beyond individual parameter docs, enriching understanding of view, line_codes, cost_centre_ids, and page_token. Given the high schema coverage, a 4 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 opens with 'Read the existing budget-or-prior variance report for a month; it never recalculates it.' This clearly identifies the action (read), the resource (existing variance report), and the scope (budget/prior, monthly). It distinguishes this from sibling read tools like get_budget or get_statement_figures by specifying the variance-report resource and its read-only, non-recalculating nature.

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?

The description establishes usage context by stating it reads an existing report and never recalculates, implying it should be used when a pre-computed variance report is needed. It also provides practical guidance: 'Filter lines or centres before paging' and the page_token restart condition. However, it does not explicitly name alternative tools or state when not to use it, so it falls short of a 5.

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