Skip to main content
Glama
Sign In

OrgGen AI

by ai.orggen
OverviewDiscussionsAdmin

set_action_status

Destructive

Ticks/unticks or updates ONE action by its text (partial, case-insensitive match): status (todo/doing/done/blocked), done, assignee, due, priority, complexity (xs..xl), labels (tags). Without cellId, searches the whole schema and flags ambiguities. It covers "mark X as done", "assign Y to Marc", "set Z's due date to Friday", "tag W as urgent" without rewriting the content block, where update_content_block replaces all its entries.

Input Schema

NameRequiredDescriptionDefault
dueNoChange the due date (null to remove)
doneNoTick/untick directly (equivalent to status done/todo)
cellIdNoID of the block carrying the action. Omitted = search across the whole schema (error listing the candidates if ambiguous)
labelsNoUser-defined labels (replaces the list; [] to remove all)
statusNoNew state ('done' ticks the action, going back to 'todo' unticks it)
assigneeNoChange the assignee (null to remove)
priorityNoFixed 4-level priority ('normal' removes the chip)
actionTextYesText (or distinctive fragment) of the action to modify — case-insensitive match
complexityNoComplexity of the entry (null to remove). RELATIVE order of magnitude in HUMAN TIME: xs = under an hour · s = a few hours · m = half a day to a day · l = a few days · xl = to SPLIT. It is estimated ahead of the pick-up of the work; it is an estimate, not a promise. No value = not estimated.
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. Changed10 schema fields changed
    • changedInput schema / properties / actionText / description
      Previous value: -"Texte (ou fragment distinctif) de l'action à modifier — match insensible à la casse"New value: +"Text (or distinctive fragment) of the action to modify — case-insensitive match"
    • changedInput schema / properties / assignee / description
      Previous value: -"Changer le responsable (null pour retirer)"New value: +"Change the assignee (null to remove)"
    • changedInput schema / properties / cellId / description
      Previous value: -"ID de la cellule portant l'action. Omis = recherche dans tout le schéma (erreur listant les candidats si ambigu)"New value: +"ID of the block carrying the action. Omitted = search across the whole schema (error listing the candidates if ambiguous)"
    • changedInput schema / properties / complexity / description
      Previous value: -"Complexité de l'entrée (null pour retirer). Ordre de grandeur RELATIF en TEMPS HUMAIN : xs = moins d’une heure · s = quelques heures · m = une demi-journée à un jour · l = quelques jours · xl = à DÉCOUPER. Elle s’estime AVANT la prise du travail ; c’est une estimation, jamais une promesse. Sans valeur = non estimée."New value: +"Complexity of the entry (null to remove). RELATIVE order of magnitude in HUMAN TIME: xs = under an hour · s = a few hours · m = half a day to a day · l = a few days · xl = to SPLIT. It is estimated ahead of the pick-up of the work; it is an estimate, not a promise. No value = not estimated."
    • changedInput schema / properties / done / description
      Previous value: -"Cocher/décocher directement (équivalent status done/todo)"New value: +"Tick/untick directly (equivalent to status done/todo)"
    • changedInput schema / properties / due / description
      Previous value: -"Changer l'échéance (null pour retirer)"New value: +"Change the due date (null to remove)"
    • 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 / labels / description
      Previous value: -"Tags user-définis (remplace la liste ; [] pour tout retirer)"New value: +"User-defined labels (replaces the list; [] to remove all)"
    • changedInput schema / properties / priority / description
      Previous value: -"Priorité fixe 4 niveaux ('normal' retire le chip)"New value: +"Fixed 4-level priority ('normal' removes the chip)"
    • changedInput schema / properties / status / description
      Previous value: -"Nouvel état ('done' coche l'action, repasser à 'todo' la décoche)"New value: +"New state ('done' ticks the action, going back to 'todo' unticks it)"
  2. Changed1 schema field changed
    • changedInput schema / properties / complexity / description
      Previous value: -"Complexité de l'entrée (null pour retirer). Ordre de grandeur RELATIF en TEMPS HUMAIN : xs = moins d’une heure · s = quelques heures · m = une demi-journée à un jour · l = quelques jours · xl = à DÉCOUPER. Pose-la AVANT la prise du travail ; c’est une estimation, jamais une promesse. Sans valeur = non estimée."New value: +"Complexité de l'entrée (null pour retirer). Ordre de grandeur RELATIF en TEMPS HUMAIN : xs = moins d’une heure · s = quelques heures · m = une demi-journée à un jour · l = quelques jours · xl = à DÉCOUPER. Elle s’estime AVANT la prise du travail ; c’est une estimation, jamais une promesse. Sans valeur = non estimée."
  3. First observed

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so safety framing is covered. The description adds real value by disclosing the partial, case-insensitive matching behavior and that ambiguity produces a candidate-listing error rather than a silent guess. However it does not state what happens when nothing matches, nor that field updates overwrite existing values (labels replacement is only visible in 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 verb and the match mechanism, then the field list, then the contrasting sibling. The parenthetical enumeration and quoted examples make it dense but every clause carries information; the final clause on update_content_block earns its place as the disambiguation.

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?

For a 10-parameter mutation tool with annotations but no output schema, the definition covers matching semantics, scope of search, ambiguity handling and the sibling alternative. Remaining gaps are the no-match case and return/confirmation behavior, which are minor given the annotations and full schema coverage.

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 goes further by explaining how actionText matching works (partial fragment, case-insensitive) and the behavioral consequence of omitting cellId. It does not add detail on expectedProjectId or the null-to-clear semantics beyond what the schema already documents.

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 (ticks/unticks/updates) applied to a specific resource (ONE action matched by its text) and enumerates the mutable fields, so an agent immediately knows this is a targeted action-attribute mutation rather than a content edit.

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 concrete usage examples ('mark X as done', 'assign Y to Marc', 'set Z's due date to Friday') and explicitly names the alternative: update_content_block is for replacing all entries, this tool avoids rewriting the content block. It also explains the no-cellId fallback (searches the whole schema and flags ambiguities), which is exactly the decision point an agent faces.

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