Dirtsmith-built (beta). Extract tables from a text-layer PDF URL as CSV, up to 5 pages per call. No OCR: scanned image PDFs return an error. Free 25/day; a /work/v2 credit unlocks 500 calls.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| pages | No | e.g. 1-3 | |
| credit | No |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | ||
| url | Yes | ||
| via | Yes | ||
| pages | Yes | ||
| quota | Yes | ||
| tables | Yes | ||
| num_pages | Yes | ||
| text_layer | Yes | ||
| checked_job | Yes |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "checked_job": {
+ "properties": {
+ "optional": {
+ "type": [
+ "boolean",
+ "null"
+ ]
+ },
+ "page": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "post_json": {
+ "properties": {
+ "fields": {
+ "properties": {
+ "email": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "need": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "source": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "use_case": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": [
+ "object",
+ "null"
+ ]
+ },
+ "to": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": [
+ "object",
+ "null"
+ ]
+ },
+ "what": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "when": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": [
+ "object",
+ "null"
+ ]
+ },
+ "num_pages": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "ok": {
+ "type": [
+ "boolean",
+ "null"
+ ]
+ },
+ "pages": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "quota": {
+ "properties": {
+ "limit": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "ok": {
+ "type": [
+ "boolean",
+ "null"
+ ]
+ },
+ "tier": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "used": {
+ "type": [
+ "number",
+ "null"
+ ]
+ }
+ },
+ "type": "object"
+ },
+ "tables": {
+ "items": {
+ "properties": {
+ "cols": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "csv": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "fill": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "numeric_share": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "page": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "rows": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "table": {
+ "type": [
+ "number",
+ "null"
+ ]
+ }
+ },
+ "type": [
+ "object",
+ "null"
+ ]
+ },
+ "type": [
+ "array",
+ "null"
+ ]
+ },
+ "text_layer": {
+ "type": [
+ "boolean",
+ "null"
+ ]
+ },
+ "url": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "via": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "required": [
+ "ok",
+ "url",
+ "pages",
+ "num_pages",
+ "text_layer",
+ "tables",
+ "checked_job",
+ "via",
+ "quota"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuinely useful behavior: a hard 5-page-per-call limit, failure on scanned/image PDFs, a 25/day free quota, and a credit-based upgrade. It does not explain what happens with PDFs longer than 5 pages (pagination/continuation), which is the main remaining gap.
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 short sentences, front-loaded with the core action and format, then constraints, then cost. The '(beta)' branding is minor filler, but every other clause delivers operational information an agent needs.
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 an output schema present, return-value explanation is not required, and the description instead covers the constraints that actually matter (OCR limitation, page cap, quotas). It is close to complete for a 3-parameter extraction tool; only the >5-page behavior is unaddressed.
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 low (33%): 'url' and 'credit' have no schema descriptions and 'pages' only has 'e.g. 1-3'. The description partially compensates by clarifying that the URL must point to a text-layer PDF and by explaining that a /work/v2 credit unlocks 500 calls, but the 'pages' range syntax and the credit parameter's accepted values remain largely undocumented in prose.
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?
It names a specific verb and resource ('Extract tables from a ... PDF URL as CSV'), which is unambiguous. It does not, however, differentiate itself from the very similar sibling 'table_to_csv' or from 'read_page', so an agent choosing between them gets no routing help from the name or description.
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 implicitly scopes usage ('text-layer PDF URL', 'No OCR: scanned image PDFs return an error'), which tells the agent when this tool will fail, but it never states when to prefer it over table_to_csv or other siblings. Usage is implied rather than explicitly routed.
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.