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

With no annotations, the description carries the full disclosure burden. It usefully states the return value ("Returns the new task id") and the API-key requirement, but says nothing about failure modes, whether invalid stage ids or unknown projectId cause errors, or whether dependencies must pre-exist — material gaps for a write tool with zero annotation coverage.

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 sentences, front-loaded with the action and prerequisite, then a compact enumeration of the optional parameter families. The middle sentence is long and runs three clauses together, which costs a bit of scannability, but nothing is wasted.

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 15-parameter mutation tool with no annotations and no output schema, the definition covers the essentials: what it creates, where it lives, how to attach hierarchy/dependencies/owners, and what it returns. It still leaves the agent guessing about validation behavior, required permissions beyond the API key, and what happens when optional references are invalid.

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 73%, and the description still adds orientation value by grouping the 15 parameters into three intents: hierarchy (parentId/phase), sequencing (dependencies), and ownership (assigneeId = person vs agentLabel = bot). The person-vs-bot distinction is the key semantic trap here and is called out explicitly, though a few sentences largely restate what the schema already says.

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?

"Add one task to an existing project" gives a specific verb (add/create) and resource (task) with an explicit scope limit (one task, existing project, connected account). This is cleanly distinguishable from siblings like create_project, create_gantt, and update_task without opening any 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?

It states a prerequisite (a LoopGantt API key) and implicitly routes agents that need grouping, sequencing, or ownership to parentId/dependencies/assigneeId. However, it never says when NOT to use it (e.g. use update_task to modify, complete_task to finish, create_gantt for bulk scheduling), so the agent must infer the boundary with siblings.

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