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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes further by warning that micro-entity filings yield nulls rather than zeros and that figures must not be mixed with ledger data. It does not discuss pagination or how many years are returned, a minor gap.

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?

Four dense sentences, well front-loaded with the return contents before the usage trigger and the important caveats. Slightly long but every sentence carries distinct information (fields, when to use, comparability warning, null semantics).

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?

No output schema exists, and the description compensates by enumerating the returned lines (balance sheet items, employees, turnover, profit after tax, reserves movement). An agent has everything needed to call and interpret results.

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 description coverage is 100% and the single optional `company` parameter is fully documented in the schema. The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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 resource (year-by-year figures from accounts filed at Companies House) and enumerates the exact contents returned, ordered newest first. It draws a sharp line against sibling tools like get_profit_and_loss and get_balance_sheet by insisting these are registry snapshots, not ledger figures.

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?

Gives explicit triggers (user asks how a prior year went, how the business has grown, what was filed, or wants past figures beside current books) and an explicit alternative context (live ledger tools). It also prescribes behavior: say "as filed" and never blend with live figures.

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