search_codesFree-text search across brands, categories and offers, e.g. 'stock perps discount', 'esim', '20% off exchange'. Returns matching verified-code records.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search terms |
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | ||
| results | Yes |
Changes observed during successful MCP inspections.
Output schema / properties / results / items / properties / expires_at / descriptionPrevious value: -"The publisher's codes have no expiry date."New value: +"No fixed expiry timestamp is recorded. Consult validity and benefit_detail for trial windows and program conditions."Output schema / properties / results / items / properties / validity / constRemoved value: -"no-expiry"Output schema / properties / results / items / properties / validity / enumAdded value: +[
+ "no-expiry",
+ "terms-dependent"
+]Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": false,
+ "properties": {
+ "count": {
+ "type": "integer"
+ },
+ "results": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "aliases": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "benefit": {
+ "type": "string"
+ },
+ "benefit_detail": {
+ "type": "string"
+ },
+ "brand": {
+ "type": "string"
+ },
+ "category": {
+ "type": "string"
+ },
+ "code": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "country_notes": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "expires_at": {
+ "description": "The publisher's codes have no expiry date.",
+ "type": "null"
+ },
+ "how_to_apply": {
+ "type": "string"
+ },
+ "keywords": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "last_verified": {
+ "description": "ISO date of the historical check recorded in the verification log, not an expiry date.",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "review_url": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "signup_url": {
+ "type": "string"
+ },
+ "slug": {
+ "type": "string"
+ },
+ "status": {
+ "const": "active",
+ "type": "string"
+ },
+ "url": {
+ "type": "string"
+ },
+ "validity": {
+ "const": "no-expiry",
+ "type": "string"
+ },
+ "verification_log_url": {
+ "type": "string"
+ },
+ "verification_methods": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "brand",
+ "slug",
+ "category",
+ "code",
+ "benefit",
+ "benefit_detail",
+ "status",
+ "validity",
+ "expires_at",
+ "last_verified",
+ "verification_methods",
+ "verification_log_url",
+ "aliases",
+ "country_notes",
+ "url",
+ "review_url",
+ "signup_url",
+ "how_to_apply",
+ "keywords"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "count",
+ "results"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description does add real context beyond the annotations: the search spans brands, categories and offers, and the results are 'verified-code records' rather than raw or all codes. It says nothing about match ranking, result caps, or empty-result behavior.
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?
One sentence for scope, one for the return, with the examples inline. No filler, no restatement of the title, and the searchable-domain information is front-loaded.
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 single-parameter, read-only search with an output schema and annotations already in place, the description is close to sufficient: it covers domain, query style, and result nature. The only gap is ranking, pagination or result-limit behavior, which is minor given the output schema exists.
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 100% so the baseline is 3, and the description earns a bump by showing the actual shape of the query string through three examples. Those examples establish that 'query' is natural-language free text and not an ID or structured filter, which the schema's 'Search terms' alone does not convey.
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 ('free-text search across brands, categories and offers') and specifies what it matches over, with concrete query examples. It never names the siblings get_code or list_brands, so an agent must infer that this retrieves multiple codes rather than one by ID or a brand list, but the purpose itself is unmistakable.
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 examples ('stock perps discount', 'esim', '20% off exchange') imply a query-shaped task and thereby imply when to reach for this tool, but there is no explicit statement of when to use it versus get_code or list_brands, and no exclusions. Usage is inferable rather than stated.
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.