Skip to main content
Glama

Check what the workspace already covers

flypost_check_coverage
Read-only

Check candidate post ideas against everything this workspace already has BEFORE writing or saving them: existing ideas and concepts, the angle and draft text underneath them, free-form drafts with no idea row, and the posts the user has ALREADY PUBLISHED. Published posts are the ones that bite — a post written outside Flypost has no idea row, so flypost_list_ideas cannot see it; it lives in the Brain and only this tool checks there. Pass every candidate title in one call. Each comes back with a verdict: "duplicate" (drop it or change the angle), "related" (the neighbours are listed, pick a distinct angle), or "clear". Every match says matched_on: "title" when two headlines collide, or "body" when the headlines look nothing alike but the argument underneath one of them is already made — body matches carry an excerpt showing the passage that collided, so read it before you dismiss them. Scoring is word overlap, not meaning, so "clear" means no overlap was found rather than definitely new. A title alone misses a published post that makes the same argument in other words: pass candidates with each idea's angle (and its post text once written) and they are also compared on substance against every published post in full — matched_on "substance" means it REPEATS that post. An idea that already exists as a row (brainstorm just made it) must pass its content_bank_item_id so it is not reported as its own duplicate. Cheap and fast — no AI billing — so run it every time you generate ideas.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "flypost_check_coverage"
  }
}

Input Schema

NameRequiredDescriptionDefault
topicsNoCandidate idea titles (or short topic descriptions) to check. Send them all at once.
candidatesNoCandidates with their substance (prefer this over topics).
project_idNoProject id; omit for the active project.
exclude_idsNocontent_bank / draft ids never to report.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint/openWorldHint=false, but the description adds substantial context beyond them: no AI billing, the three verdict values and what each implies for action, the matched_on taxonomy (title/body/substance) with an explanation of why body matches carry excerpts, and the honest limitation that scoring is word overlap rather than semantics so 'clear' is not a guarantee of novelty.

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 purpose is front-loaded in the first clause and the ordering (what it checks → verdicts → match types → caveats → cost) is logical. It is on the long side with some restatement — the one-call batching instruction appears in both description and schema, and the emphasis capitals ('ALREADY PUBLISHED', 'REPEATS') are doing work that sentence structure could do — but little is genuinely redundant for a tool with this much nuance.

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?

There is no output schema, so the description carries the full burden of describing returns, and it does: verdict values, matched_on values, and the excerpt field for body matches. Combined with the cost note and the documented blind spots, an agent has everything needed to call it and interpret the result without guessing.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline would be 3, but the description adds real meaning: it explains the consequence of omitting angle/body (a title alone misses published posts that make the same argument differently) and why content_bank_item_id must be supplied (so a just-created idea is not reported as its own duplicate). These are causal rationales the schema does not carry.

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?

States a specific verb and resource — checks candidate post ideas against everything the workspace already contains — and enumerates the corpora searched (existing ideas, angles, draft text, free-form drafts, published posts). It explicitly distinguishes itself from flypost_list_ideas by explaining that published posts have no idea row and only this tool reaches the Brain.

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?

Gives an explicit timing rule ('BEFORE writing or saving them'), an explicit alternative and its failure mode (flypost_list_ideas cannot see published posts), and a frequency recommendation ('run it every time you generate ideas'). It also states the batching rule — pass every candidate title in one call — so the agent knows how to invoke it, not just when.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.