Skip to main content
Glama

plan_crawl

Idempotent

Compiles concepts, entity scope, and dates into a ranked, failover-aware crawl plan without fetching data; reports unroutable concepts and unmapped entities instead of dropping them.

Instructions

Plan a concept crawl -> CrawlPlan artifact (concepts in, methods out).

Compiles desired concepts + entity scope + date range into a ranked, failover-aware CrawlPlan. Does not fetch. Unroutable concepts (no confirmed binding) and unmapped entities (no per-source identifier) are reported, not silently dropped.

If since_last is True, the plan's date_range.start is derived from the minimum per-concept max(date) already in semantic_observations (incremental crawl). Either start or since_last must be provided. If both, start wins. end defaults to today if not provided.

mode is per_date (one request per concept x entity x date) or series (one request per concept x entity against a bulk_history endpoint; the pipeline explodes the returned frame). Series mode refuses concepts bound only to non-bulk functions.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "concept_ids": "<concept_ids>",
      "entity_type": "<entity_type>"
    },
    "name": "plan_crawl"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
modeNoper_date
startNo
frequencyNo
entity_idsNo
since_lastNo
concept_idsYes
entity_typeYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare non-destructive, idempotent, closed-world behavior, and the description adds real behavioral detail on top: unroutable concepts and unmapped entities are reported rather than silently dropped, series mode refuses concepts bound only to non-bulk functions, and precedence rules ('start' wins, 'end' defaults to today). These are non-obvious failure and validation semantics an agent could not infer from the schema.

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?

Front-loaded with the purpose in the first line, then organized into scope, date-handling, and mode paragraphs — each carrying distinct information. Slight redundancy between the subtitle '(concepts in, methods out)' and the 'Compiles desired concepts...' sentence, but no filler.

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

Completeness4/5

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

An output schema exists, so return-value description is unnecessary, and the tool's complexity (8 params, plan generation, failover) is largely addressed through the date-range, mode, and reporting semantics. The main residual gap is the unexplained `frequency` and entity-scoping parameters.

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

Parameters3/5

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

Schema description coverage is 0%, so the description must carry parameter meaning; it explains `start`, `since_last` (derived from per-concept max(date) in semantic_observations), `end` default, and the two `mode` values with real semantics. However, `frequency`, `entity_ids`, and `entity_type` get no direct explanation, leaving part of the 8-parameter surface undocumented.

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 states a specific verb and resource — 'Plan a concept crawl -> CrawlPlan artifact' — and immediately clarifies the transformation ('concepts in, methods out') plus the boundary 'Does not fetch', which distinguishes it from the sibling `fetch`.

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

Usage Guidelines4/5

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

It clearly establishes the context: compile concepts plus entity scope plus date range into a plan, and explicitly that it does not fetch data (implying `fetch` executes the plan). It also states validation prerequisites, such as 'Either ``start`` or ``since_last`` must be provided' and that series mode refuses non-bulk-bound concepts. It stops short of naming the follow-up tool to run the plan.

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