Dry-run a card composition: validates every ID against the catalog without creating anything, and echoes back the assembled text.
| Name | Required | Description | Default |
|---|---|---|---|
| occasion | Yes | ||
| offer_id | Yes | ||
| holiday_id | No | ||
| phrase_ids | Yes | ||
| signoff_id | Yes | ||
| template_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It clearly discloses that this is non-destructive ('without creating anything') and echoes text back, which is important behavioral context. However, it doesn't specify error behavior or output structure, which would be more thorough.
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?
Two sentences, no fluff, directly states purpose and behavior. Highly concise.
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?
Covers the basic purpose and non-destructive nature, but lacks details on output format, error handling, and parameter specifics. Given 6 parameters and no output schema, it could be more complete.
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 0%, and the description doesn't explain any parameters beyond 'every ID'. It doesn't add meaning to template_id, phrase_ids, offer_id, holiday_id, or occasion. The description must compensate for the lack of schema annotations but does not.
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 clearly states the tool's purpose: it performs a dry-run of a card composition, validates IDs, and echoes back assembled text. The verb 'validates' and resource 'card composition' distinguish it from send_card, which likely creates/sends.
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 implies usage (before sending, to validate IDs) but doesn't explicitly state when to use this versus alternatives like send_card or get_card_templates. It gives context but no exclusions or explicit when-not-to-use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool targets a distinct resource or action: bounties are list/claim/check, card composition is template/offer/phrase selection, and send_card is clearly separated from send_sample_card and preview_card. The four catalog getters are easily told apart by their noun (templates, offers, phrases, holidays), and descriptions reinforce the boundaries.
All tools follow a consistent snake_case verb_noun pattern: get_* for listing, send_* for delivery actions, preview_card for dry-run, and submit/check for bounty workflow. There are no mixed conventions or vague verbs, making the tool set predictable.
Ten tools is well within the ideal range and each tool earns its place. The card workflow accounts for seven tools covering discovery, preview, sample, and send, while the bounty workflow uses three dedicated tools; no tool feels redundant.
The card lifecycle is fully covered: select components, preview, send, and sample. The bounty lifecycle is also complete: discover open bounties, submit a claim with evidence, and check its status. There are no obvious dead ends or missing core operations for the stated domain.