Skip to main content
Glama

This week's social posts

social_set

The plan for this week's 6 short posts for TikTok, Instagram Reels and YouTube Shorts (the same post on each) and X (routines/posts.md): each post's format, the audience its hook is written for and the local time it goes out (every week the screen slideshow and the AI presenter, then formats in turn, least recently posted first, the one with the most views always in); the guide for every format (what it is, where the product shows, what keeps it true, the kit frames it is made of); the founder's goal and audiences; last weeks' views per format; and where each platform schedules. Pass the founder's time zone. Pass goal and audiences the first time (the audiences: the 2 or 3 people the product is for, in their own words, read from the site; the founder confirms them), and remakes when the founder linked posts that worked. Saves nothing about posts; social_posts_save does. Free.

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": {
      "tz": "<tz>"
    },
    "name": "social_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
tzYesThe founder's IANA time zone, from their machine ("Europe/Istanbul")
goalNoWhat the founder wants most from the posts. Asked once, then kept
remakesNoLinks to posts that worked, to remake for this product
audiencesNoThe 2 or 3 people the product is for, in their words. Kept

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.4/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, but the description adds context the annotations cannot carry: 'Saves nothing about posts; social_posts_save does' resolves what the non-read-only hint actually means, and 'Free' discloses the cost profile. The 'Asked once, then kept' / 'Kept' wording also tells the agent that goal and audiences persist across calls, which is genuine behavioral information beyond the hint flags.

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

Conciseness2/5

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

One enormous run-on sentence with nested parentheses carries almost the entire definition, then a second sentence bolts on parameters, followed by a bare 'Free.' at the end. The most actionable content (which parameters to pass and when) is buried after a long inventory of return contents. It is not padded with filler, but the structure actively impedes scanability.

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?

With no output schema, the description must carry the return-value burden, and it does enumerate the plan's contents substantially (formats, hooks/audiences, local times, format guides, last week's views, scheduling locations). It also covers the required parameter and both conditional parameters, plus cost and persistence. Missing only the shape/format of the response, which is a minor gap against an otherwise thorough inventory.

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?

Schema coverage is 100%, so a 3 is the floor, and the description earns above that by supplying the conditional logic the schema omits: goal and audiences are only optional in the schema but the description says to pass them 'the first time (the founder confirms them)', and remakes only 'when the founder linked posts that worked'. It also clarifies tz must be the founder's time zone, reinforcing the schema's own note. The dense phrasing of the audiences explanation ('the 2 or 3 people the product is for, in their own words, read from the site') repeats the schema description rather than extending it.

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

Purpose3/5

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

The description enumerates in detail what the returned plan contains (post formats, audiences, local send times, format guides, goal, audience, last week's views, platform schedules), so the resource is identifiable. But no verb ever states what the tool does to that resource — it opens with a noun phrase ('The plan for this week's 6 short posts...') and the agent has to infer it assembles/returns a weekly plan. It does explicitly separate itself from social_posts_save ('Saves nothing about posts'), which helps disambiguation, but the core action remains implicit.

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

Usage Guidelines3/5

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

There is real conditional guidance for parameters — 'Pass goal and audiences the first time' and 'remakes when the founder linked posts that worked' — plus an implicit boundary against social_posts_save for saving. What is missing is when to call this tool at all versus siblings like plan, aso_set or social_setup: there is no 'call this at the start of each week' or exclusion statement. Usage is inferable but not stated.

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.