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

Annotations already cover read-only, idempotent, open-world, non-destructive behavior, but the description adds substantial behavioral context beyond them: pagination is hard-capped at 50 rows with total_results/total_pages in the response, 50 rows 'is a page, never the whole change history,' and rows disclose whether a change has actually been APPLIED vs. merely made. It also names the underlying source feed, which is valuable for trust calibration.

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?

It is dense and long, but front-loads the core purpose, example phrasings, and the critical pagination warning ahead of lower-priority source attribution. Almost every sentence carries information, though the length is close to the upper useful bound for a tool description.

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?

Though no output schema exists, the description describes the returned row structure in detail (amending/amended instrument, affected/affecting provisions, change type, applied status, commencement date), plus pagination fields and the direction switch. An agent has everything needed to call and interpret results 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?

Schema description coverage is 100%, so the schema already documents all five parameters including the 'direction' and 'page' semantics. The description largely restates the direction definition already present in the schema and adds no parameter syntax or format detail beyond it, so the baseline of 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 verb+resource pair with bidirectional scope: 'what has amended this UK Act or instrument, and (in the other direction) what this legislation itself amends.' It also grounds it with concrete example phrasings ('what has changed the Data Protection Act 2018') that an agent can map to a request, and it is clearly distinct from siblings like get_legislation, get_legislation_section, and get_legislation_text.

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 clear context via example queries and explicitly distinguishes the two operating modes of the 'direction' parameter, telling the agent which mode suits which question. It does not name sibling tools or state when to prefer them over this one (e.g., text retrieval vs. amendment history), so it falls just 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.