Skip to main content
Glama

tap_run

Run a pre-built tap to extract structured data from a site. Returns columns, rows, count, and timing. Uses deterministic logic, no AI. Results cached for 5 minutes; use fresh:true to force refresh.

Instructions

Run a pre-built tap. Preferred over tap.* tools — deterministic, zero AI at runtime. Returns {columns, rows, count, timing, cache_hit}. Read-intent taps are memoized for 5 minutes per process; identical calls return cached data with cache_hit:true. Pass {fresh:true} to bypass cache. Write-intent taps are never cached. If rows contain login/error page content or are empty on a site that requires login → call tap.runtime(runtime:'chrome') first, then retry. If rows is empty on a public site, use tap.doctor(site, name) for structured diagnosis. On transient failure (timeout, connection), RETRY tap.run — do not fall back to manual tap.* operations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
siteYesSite name
nameYesTap name
argsNoTap arguments
freshNoBypass the 5-minute per-process result cache. Use when you need current data despite a recent identical call.
envelopeNoResponse shape. 'bare' (default) returns {rows, columns, count, elapsed_ms}; 'annotation' wraps the result in a W3C Web Annotation with target + body:tap:RunResult + prov:wasDerivedFrom — useful for provenance chains and signing. Does NOT affect sub-tap composition or pipe bindings (those read the internal flat shape).bare
Behavior5/5

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

The description thoroughly discloses behavioral traits: caching behavior (5-minute memoization per process, fresh parameter to bypass), distinction between read-intent (cached) and write-intent (never cached), and the exact return format including cache_hit flag. It also explains how to handle login/error pages and transient failures. Annotations add no further information, but the description covers everything an agent needs to understand side effects and state changes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and return shape. Every sentence serves a purpose — caching behavior, guidance for failure cases, and links to sibling tools. It is slightly dense but not verbose; each sentence earns its place. Minor improvement could be splitting into bullet points, but as prose it remains effective.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (caching, multiple failure modes, interaction with sibling tools), the description is complete. It specifies exact return fields despite lacking an output schema, details caching and freshness, and provides explicit fallback paths for three different failure scenarios. No gaps remain for an agent to guess behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with descriptions for all 5 parameters, so the bar is lowered. However, the description adds value beyond the schema by explaining the envelope parameter's two modes ('bare' vs 'annotation') and their implications for provenance. It also clarifies that fresh bypasses the 5-minute cache, which aligns with the schema description but reinforces usage intent.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Run a pre-built tap.' It distinguishes from sibling tools by claiming it is 'Preferred over tap.* tools — deterministic, zero AI at runtime.' The return shape {columns, rows, count, timing, cache_hit} is also specified, leaving no ambiguity about what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool (preferred over manual tap.* operations) and when not to: if rows contain login/error content or are empty on a site requiring login, use tap.runtime first; if empty on a public site, use tap.doctor. It also advises to retry on transient failures rather than falling back to manual operations. This is comprehensive decision support.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LeonTing1010/tap'

If you have feedback or need assistance with the MCP directory API, please join our Discord server