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

Annotations only declare destructiveHint=true, and the description substantially enriches this: deletion removes the project, its checks and digests permanently while research stays in history, pausing frees the plan slot, and reactivation consumes a free slot. It also flags a human confirmation requirement before destructive action.

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?

A single dense sentence with parenthetical mode glosses, front-loading 'pauses... follows... stops following' then qualifying each. Nothing is wasted, though the nested parentheses make it slightly harder to scan than a clean list.

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 and minimal annotations, the description covers consequences, preconditions and the human-confirmation need. It still omits what happens on failure (e.g., activating with no free plan slot) and does not mention the follow_niche relationship.

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 the baseline is 3, but the schema's own status description merely restates the enum values. The description adds genuine semantics for each value (freed plan slot, required free slot, permanent removal, history retention) that the schema does not convey.

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 gives a specific verb+resource+effect: it updates a followed project's status to one of three named states and describes what each one means. It fails to differentiate from the sibling follow_niche, which also causes a project to become 'active', so the agent must infer the boundary.

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 clear per mode: pause frees the plan slot, active requires a free slot, deleted is permanent, and the user should be asked before deleting. There is no explicit 'prefer X over Y' routing against follow_niche, so it stops short of full when/when-not guidance.

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