Get Filed Accounts History

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description correctly adds deeper behavioral context rather than repeating them: the data is a registry snapshot rather than the live ledger, the agent should present it 'as filed', and micro-entity filings should be reported as lacking turnover/profit rather than coerced to zero. This is exactly the kind of interpretive guidance annotations cannot express.

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 (~100 words) but every clause earns its place: content inventory, usage triggers, provenance warning, and the micro-entity caveat. The most decision-relevant information (what it returns) is front-loaded, though the opening sentence is long and could arguably be split.

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, read-only tool with no output schema, the description is fully self-sufficient: it explains what data comes back, the ordering (newest first), the edge case for micro-entities, and how to present results. An agent has everything needed to invoke it correctly.

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 has zero parameters and schema coverage is 100%, so the baseline is 4 per the rubric. The description does enrich the semantics by explaining what the returned figures represent and how to interpret edge cases like micro-entity nulls, which compensates for the absence of an output schema.

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 a specific verb-resource pair ('year-by-year figures from the accounts this company has filed at Companies House, newest first') and enumerates the exact content: balance sheet lines, average employees, turnover, profit after tax, and reserves movement. It differentiates from sibling tools by contrasting registry snapshots with the live ledger, so an agent can distinguish it from get_profit_and_loss or get_balance_sheet.

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 gives explicit when-to-use triggers ('Use when the user asks how last year or an earlier year went, how the business has grown, what was filed, or wants past figures beside the current books') and a clear when-not: never blend these registry figures with live ledger numbers. It stops short of naming specific alternative sibling tools, but the ledger contrast effectively routes the agent.

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