Removes the project link carried by a block. The linked project is not affected — only the pointer disappears from this schema.
| Name | Required | Description | Default |
|---|---|---|---|
| cellId | Yes | The id of the block whose link must be removed. | |
| expectedProjectId | No | 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. |
Changes observed during successful MCP inspections.
Input schema / properties / cellId / descriptionPrevious value: -"L'identifiant du bloc dont il faut retirer le rattachement."New value: +"The id of the block whose link must be removed."Input schema / properties / expectedProjectId / descriptionPrevious 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."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare destructiveHint=true, but the description usefully narrows the blast radius: the linked project is untouched and only the pointer on this schema disappears. That is real added context beyond the annotation. It does not mention idempotency or what happens if no link exists, which keeps it below a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, zero filler, with the core effect first and the non-obvious side-effect boundary second. Nothing repeats the schema or annotations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter mutation with no output schema, the effect and its main side-effect boundary are covered. Minor gaps remain around behavior when no link is present and whether link metadata is lost, but the schema and annotations carry the rest.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so cellId and expectedProjectId (including the cross-project override and its refusal behavior) are already fully documented in the schema. The description adds no parameter detail, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Removes the project link carried by a block') and the second sentence delimits scope by making clear the project entity itself survives. An agent can contrast it directly with link_project_to_cell and delete_project 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied — it is the inverse of link_project_to_cell — but the description never names that sibling or says when to use this instead of delete_cell, update_cell, or fork_linked_project. No prerequisites or exclusion conditions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.