Skip to main content
Glama
Sign In

Conciergr Timetable

by com.conciergr
OverviewDiscussionsAdmin

Tell the Timetable team about a problem

give_feedback

Report a problem with Conciergr Timetable to the team that builds it. They read every report, investigate it and fix what is theirs. Call it, without asking the person first, when: a tool's result contradicts its description or the guide; a refusal doesn't say how to fix it, or you can't get past it after doing what it says; a call fails with "Something went wrong on our side"; a description or the guide misled you or left you guessing; or the person needs something no tool does. Also when the person asks you to pass something on. One report per problem, sent once, after you have tried what the refusal said. In details say what you were doing for the person, the tool and arguments you sent, what came back and what you expected. Leave out children's and families' names and contact details: describe them instead. Then tell the person in one line that you reported it and carry on: nothing waits for an answer, and a report changes nothing in the timetable.

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": {
      "kind": "<kind>",
      "summary": "<summary>",
      "details": "<details>"
    },
    "name": "give_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesbug: something didn't work as described; unclear: a description, the guide or a refusal misled you or left you guessing; missing: the person needed something no tool does; other: anything else worth the team's time.
toolNoThe tool it is about, if one.
detailsYesWhat you were doing for the person, the tool and arguments you sent, what came back (the refusal's words), and what you expected.
summaryYesOne line: what went wrong.
asked_by_personNotrue when the person asked you to pass this on; false (the default) when you noticed it yourself.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=false, destructiveHint=false), it discloses what an annotation cannot: nothing in the timetable changes, no reply ever arrives, so the agent shouldn't wait, and it must tell the person in one line afterwards. It also imposes a privacy constraint on report contents that the schema does not express.

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?

Purpose is front-loaded and the long trigger list is the necessary payload, with the workflow (one report, sent once, then a one-line notice) following in a logical order. The single dense paragraph could be split for scanability, but there is no filler to cut.

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?

For a five-parameter mutation tool with no output schema, this covers everything an agent needs: when to fire, what to put in each field, what happens afterwards (nothing), and what to tell the user. The absence of a return value is explicitly addressed rather than left ambiguous.

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 the baseline is 3 and the field-by-field meaning is already documented. The description still adds non-schema content rules — specify the tool and arguments sent, quote what came back, state the expectation, and strip children's and families' names and contact details in favour of describing them.

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 opening sentence names a specific verb and resource — "Report a problem with Conciergr Timetable to the team that builds it" — and immediately scopes the audience. Nothing among the fifty-odd CRUD siblings does anything similar, so the agent can distinguish it without opening a schema.

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?

It enumerates exact trigger conditions (result contradicts description, unhelpful refusal, "Something went wrong on our side", misleading guide, missing capability, person asks) and states a negative rule: don't ask the person first. It also gives the alternative path — try what the refusal said before filing, and file once per problem.

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

All Conciergr Timetable toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources