manage_projects

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds substantially more: deletes take child records with them after a safety copy, the response carries the undo call, and the operation blocks on user approval when approvals are on. It also discloses that names are unique and that 'archived'/'deprecated' act as retirement states. Nothing here contradicts the annotations.

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?

Very little waste: the scope sentence is front-loaded and each clause carries a distinct rule or trait. The telegraphic 'action: constraint' compression across eight actions is efficient but borders on cryptic, and a little structure (grouping reads vs mutations) would have cost nothing.

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 an eight-parameter dispatcher with no output schema, the description covers what an agent needs: which actions are reads ('Reads: list, list_components'), what deletion destroys and how to reverse it, and the approval branch. Return shape is stated in one clause ('project or component rows, or what was deleted'), which is the right amount given no output schema. Only minor gaps remain, such as pagination or ordering for list.

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 100%, so every parameter including the action enum and status enum is already documented in the schema, per-action. The description reinforces the status-per-action mapping but adds no syntax, format, or edge-case meaning beyond it. Baseline 3 applies when the schema carries the load.

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?

Each action is bound to a specific resource: 'list: projects (by status)', 'update_component', 'delete_component', and the opening clause defines the domain as projects and their named component parts. An agent can map any requested operation to an action value without opening the schema. It stops short of 5 only because the condensed clause style makes the overall scope take a moment to parse.

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?

Explicit conditional rules are given where they matter: 'create: only when the user asks' and 'delete / delete_component: only when the user asks'. It also names the sibling that takes over when approvals are enabled ('manage_review lists it'), which is a concrete alternative, not an inference.

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