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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so safety is covered. The description adds real value beyond that: it clarifies the return is the raw numeric table rather than a chart image, and notes in the example context the ordering nuance of the series. It does not discuss pagination limits or provenance caveats, keeping it at a 4.

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?

Front-loaded with the core purpose, then provenance, then use cases, then the example. Every sentence carries information, though the worked example largely duplicates what the input schema already shows, which slightly dilutes the density.

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 no output schema, the description carries the burden of describing the return, and it does state that the result is the underlying rows-and-columns table rather than an image. An agent has enough to call it correctly, though return shape details (column naming, row count behavior) rest on the schema's limit semantics.

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 limit, dataset_id, and latest_first are already fully documented in the schema, including defaults and semantics ('these series run oldest-first'). The description's example mirrors the schema example rather than adding syntax or format meaning, so 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 verb and resource ('return the full underlying table for one Ofgem Data Portal dataset as rows and columns') and explicitly distinguishes the payload from the rendered chart. An agent can immediately separate it from siblings like ofgem_datasets (which catalogs datasets) and ofgem_price_cap.

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 the exact precondition for the required parameter ('Get the dataset id from ofgem_datasets') and concrete user-intent phrasings that should trigger this tool ('monthly GB day-ahead gas price series', 'supplier market share by year'). The routing to the sibling that supplies the id is explicit, leaving little to inference.

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