Price a selection

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

The description discloses key behaviors beyond the annotations: it explicitly states 'reserves nothing', which is important given the idempotentHint is false and the tool could be mistaken as a side-effecting operation. It also reveals that it returns 'balance_credits and reserved_credits' as the only view of remaining credits for API-key callers, and notes the openWorldHint by saying 'usage pages are dashboard-only'. It also details the return contents (priced entries, exclusions with reasons, total_ceiling_credits, confirm_with) and that chart requires a category, going well beyond the annotations.

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 a single, well-structured paragraph that front-loads the most critical information ('Price a selection before spending; reserves nothing') and then goes into detail. Every sentence provides value: it names the two input modes, describes the output fields, and highlights the credit balance functionality. There is no verbosity or repetition; it is concise yet comprehensive.

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?

Given the tool's complexity (nested objects, 4 parameters, no output schema), the description is highly complete. It explains the primary use case, the required input form, the output structure (including exclusions and total_ceiling_credits), and a unique side effect (credit balance view). It also mentions the open-world nature (usage pages are dashboard-only), which is not in the schema. The description fills in nearly all gaps an agent would need to call it correctly, including the critical constraint of 'exactly one' and the confirm_with detail.

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 coverage is 50%, and the description clarifies key parameter usage: it explains that 'shows' must come from 'search_shows or chart_shows' (which is also in the schema but reinforces), and that the tool requires 'exactly one of shows or chart'. It also mentions the chart's 'category' field. However, it does not elaborate on all parameters like include_music_led or the meaning of episode_ids, but the schema provides some descriptions. The description adds the crucial constraint of 'exactly one' that is not explicit in the schema, so it adds significant value over the 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 states a specific action ('Price a selection before spending; reserves nothing') and clearly identifies what the tool does: it returns pricing information for either shows or a chart. It distinguishes itself from siblings by mentioning 'Exactly one of shows (feed URLs from search_shows or chart_shows) or a chart' and clarifies it is a pre-spend step, unlike confirm which would execute. The purpose is unambiguous and distinct from the other tools.

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 clearly states when to use this tool: 'before spending' and 'reserves nothing', indicating it is for pre-purchase evaluation. It also provides a contrast with 'confirm' by mentioning 'confirm_with (what confirm takes)' and implies the tool should be used before confirm. However, it does not explicitly list exclusions or alternatives (e.g., when to use search_shows vs quote), but the usage context is clear enough for most cases.

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