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

With no annotations provided, the description carries the full burden and does substantial work: it discloses that every returned row carries source_url and verified_at and instructs the agent to quote them, and it explains the verification posture by covering unverified rows. It does not mention pagination, result limits, or operational failure modes, but for a read-only query tool the citation-behavior disclosure is the most decision-relevant trait and it is present.

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, each earning its place: trigger conditions, data/coverage scope, filter guidance, output-citation behavior, and exclusions with alternative routings. The structure is front-loaded with the 'when to use' trigger. It is slightly long-winded ('Use this when a user asks what...') but no sentence is wasted.

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 7-parameter tool with no annotations and no output schema, the description covers triggers, data fields, coverage, and citation behavior well. However, it never disambiguates against the sibling get_uk_ev_tariffs despite the schema containing ev_tou and ev_addon tariff types that plausibly overlap, and it does not explain limit/default result behavior or how freshness relates to get_data_freshness.

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 57% (region, supplier, type, include_unverified documented in schema; fuel, limit, payment_method undocumented). The description adds domain meaning that helps fill gaps — it maps tariff types to real-world concepts (Economy 7, Agile, tracker) and explains that fuel covers electricity/gas — but it largely restates the filter parameters ('Filter by region (GSP letter), tariff type, supplier slug or fuel') rather than clarifying limit or payment_method semantics.

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 names a specific verb and resource ('get' + 'UK domestic electricity or gas tariff') and enumerates the exact data returned: unit rates (p/kWh), standing charges (p/day), off-peak windows, exit fees and SEG export rates. It also distinguishes itself from siblings by explicitly excluding public EV charging prices and the Ofgem cap, and by naming the alternative tools for those cases.

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 opens with explicit trigger conditions ('Use this when a user asks what a UK domestic electricity or gas tariff costs...') and gives explicit negative routing: 'Not for public EV charging prices (use get_ev_charging_prices) or the Ofgem cap (use get_ofgem_price_cap).' It also describes the coverage scope (Octopus Energy and other GB suppliers, standard variable through export tariffs), making the selection decision nearly unambiguous.

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