Skip to main content
Glama
Sign In

OrgGen AI

by ai.orggen
OverviewDiscussionsAdmin

suggest_horizon

PROPOSES a horizon for a block: Now (now), Next (next) or Later (later), with a one-sentence reason (at most 140 characters). ⚠️ This tool SORTS NOTHING: it files a suggestion that only the owner or a manager of the project can accept or refuse. The site has no roadmap screen for that decision yet, so the proposal exists but nothing on the site accepts or refuses it. The sorting itself is a human action — no tool sets it. The proposal is signed (it appears in the history of the block). Refused, without writing anything, if the block does not exist, if it is already in the proposed horizon, if the SAME proposal (this block, this horizon) is already awaiting a decision (duplicate_suggestion), if too many suggestions are already waiting (suggestions_full), or if agent writes are locked on this project. ⚠️ REAL idempotence, and bounded: replaying the same call (same block, same horizon, whatever the reason) is refused as a duplicate WHILE the first suggestion is PENDING; once decided (accepted or refused), you can propose again. ⚠️ As long as the roadmap is not served on this project, the call answers roadmap_unavailable and writes nothing. The current state is read with list_roadmap: a suggestion that repeats it brings nothing.

Input Schema

NameRequiredDescriptionDefault
motifYesWhy, in one sentence (at most 140 characters): the governing role reads it when accepting or refusing.
blockIdYesIdentifier of the BLOCK to sort (it must exist in this project).
proposedHorizonYesThe proposed horizon: now (Now), next (Next) or later (Later).
expectedProjectIdNoUUID of the project targeted by THIS call. ACTUALLY targets this project instead of the session project. Refused without changing anything if access is not granted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / blockId / description
      Previous value: -"Identifiant du BLOC à ranger (il doit exister dans ce projet)."New value: +"Identifier of the BLOCK to sort (it must exist in this project)."
    • changedInput schema / properties / expectedProjectId / description
      Previous value: -"UUID du projet visé par CET appel. Cible RÉELLEMENT ce projet au lieu du projet de session. Refusé sans rien modifier si l'accès n'est pas accordé."New value: +"UUID of the project targeted by THIS call. ACTUALLY targets this project instead of the session project. Refused without changing anything if access is not granted."
    • changedInput schema / properties / motif / description
      Previous value: -"Pourquoi, en une phrase (140 caractères au plus) : le gouvernant la lit en acceptant ou en refusant."New value: +"Why, in one sentence (at most 140 characters): the governing role reads it when accepting or refusing."
    • changedInput schema / properties / proposedHorizon / description
      Previous value: -"L’horizon proposé : now (Maintenant), next (Ensuite) ou later (Plus tard)."New value: +"The proposed horizon: now (Now), next (Next) or later (Later)."
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare the safety profile (non-destructive, closed-world); the description adds the real behavior: no side effect on the roadmap, proposal is signed into block history, bounded idempotence keyed on (block, horizon) while pending, plus concrete refusal codes (duplicate_suggestion, suggestions_full, roadmap_unavailable, agent writes locked). This is exactly the context annotations cannot provide.

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

Conciseness3/5

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

Front-loaded and logically ordered, but the central point ('SORTS NOTHING', no roadmap screen, human action, no tool sets it) is restated three times, and the roadmap_unavailable caveat appears in two separate places. Trimming the redundant emphasis would make it noticeably tighter without losing content.

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 four parameters, no output schema, and non-trivial failure modes, the description covers everything an agent needs: when the call is refused, what state to read first, how idempotence is bounded, and that the effect is only a signed proposal. Nothing material is missing.

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, but the description adds semantics the schema does not: the duplicate key is (block, horizon) regardless of the reason text, the motif is read by the governing role when deciding, and expectedProjectId refusal behavior. Only the retry/override nuances of expectedProjectId are left to the schema.

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?

Opens with a specific verb and resource ('PROPOSES a horizon for a block') and enumerates the three allowed values. It explicitly separates itself from any sorting or state-changing tool, naming list_roadmap as the read counterpart, so an agent can identify it without opening the 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?

States both when to use it (to file a proposal that only an owner/manager can decide) and when it is pointless ('a suggestion that repeats [the current state] brings nothing'), and points to list_roadmap for reading current state. Alternatives and exclusions are explicit rather than implied.

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

All OrgGen AI 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