Preview 1-20 Status or Priority updates for one GitHub Project and store an immutable, expiring plan without modifying GitHub.
Create an immutable, expiring M10-5 preview for 1-20 Status/Priority updates in one authorized Project. This performs reads and stores a plan but never mutates GitHub.
| Name | Required | Description | Default |
|---|---|---|---|
| owner | Yes | ||
| number | Yes | ||
| operations | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds real context beyond the annotations: annotations give readOnlyHint=false and destructiveHint=false, and the description clarifies that despite writing a stored plan it 'never mutates GitHub', plus that the preview is 'immutable' and 'expiring'. That reconciles the non-readOnly hint with actual behavior. It does not state auth requirements or how long the preview lasts.
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 front-loaded sentences with no filler; constraints (scope, cardinality, non-mutation) come early. The opaque 'M10-5' tag arguably does not earn its place, slightly weakening an otherwise tight sentence.
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?
There is no output schema, so the description should tell the agent what the preview returns and how to consume it (e.g., a plan handle to pass to approve/apply). Saying it 'stores a plan' gestures at this but never names the handoff, leaving a meaningful gap for a tool whose whole purpose is to precede a mutation.
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?
With 0% schema description coverage, the description must carry the burden, and it partially does: '1-20' maps to the operations minItems/maxItems, 'Status/Priority' maps to the field enum, and 'one authorized Project' covers owner+number. However, itemId and value semantics remain entirely unexplained in both schema and description.
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 (Create) and a well-scoped resource (an immutable, expiring preview for 1-20 Status/Priority updates in one Project), so the agent knows exactly what it produces. The 'M10-5' token is opaque internal jargon and the description never names the sibling it feeds into (approve/apply_github_project_bulk_plan), so sibling differentiation is only implied by the word 'preview'.
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 implied — the word 'preview' and 'stores a plan but never mutates' suggest this is a pre-flight step before apply_github_project_bulk_plan — but no alternative is named and no explicit when/when-not condition is given. The agent must infer the preview→approve→apply sequence from sibling names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.