Maintain projects

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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, covering the safety profile. The description adds real behavioral context beyond that: changes cascade to every phase >= N, and the auto_start advance only moves forward and stands down when project_filter/force are set. It stops short of describing the actual side effects (file edits, commits, pushes) the workflow performs.

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?

The opening sentence is front-loaded and clear, and the auto_start paragraph is dense without repetition. But the allocation is disproportionate: nearly the entire description expands one parameter while the other nine are ignored, so length is not well spent relative to the tool's surface area.

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 10-parameter, zero-coverage mutation tool with no output schema and an open-world hint, the description is incomplete. It omits most parameters, the return behavior, and any sibling differentiation, leaving an agent unable to call it correctly in many situations.

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 description coverage is 0%, so the description must carry the load, and it richly explains the interplay of auto_start, start_phase, project_filter, and force. But six of ten parameters (`part`, `config`, `dry_run`, `progress`, `single_phase`, `allow_pre_commit`) are undocumented in both schema and description — notably `part` and the safety-relevant `dry_run`. Partial compensation only.

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?

The description states a specific verb and resource: 'Execute the phased bumpversion workflow: pre-commits + phased bumping.' This is more informative than the vague tool name 'maintain_projects' and clarifies the operation. However, it does not distinguish itself from the near-identical sibling `repository_manager_phased_bumpversion`, leaving the agent unsure which one to select.

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?

The bulk of the text describes how `auto_start` behaves once invoked, not when to choose this tool over alternatives. There is no comparison to siblings like `repository_manager_phased_bumpversion`, `repository_manager_bulk_bump`, or `repository_manager_pre_commit`, and no statement of prerequisites. Tool-selection guidance is absent.

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