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

Goes well beyond the readOnly/idempotent annotations: it names the return type (LiteTaskResponse), explains that names and emails replace UUIDs, discloses the otherwise-invisible behavior that the MCP injects the workspace param for key refs, and states the required API-key scope (tasks:read). Those are exactly the non-obvious traits an agent needs.

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?

Front-loaded with purpose and ref semantics, and the internal note is compact. The trailing presentation rules (link title to webUrl, suppress raw key when displayKey is null) are useful but renderer guidance rather than invocation info, slightly diluting focus.

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?

With no output schema, the description does a solid job of summarizing the return shape (LiteTaskResponse, resolved names/emails) and the auth scope. What is missing is error behavior (e.g. invalid ref or missing workspace) and whether the ambient workspace setting matters for identifier refs.

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 already 100%, so the schema carries ref/account/workspace. The description still adds value by pairing the ref formats with the conditional workspace requirement ('when ref is a task key the workspace query param is required'), which clarifies a real interaction between two params.

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+resource ("Fetch a task by ref") and clarifies that ref accepts either a system identifier (tsk_…) or a human task key (PROJ-42). Clear enough for an agent to pick this for single-task retrieval. It stops short of naming the sibling it competes with (e.g. pm_search_tasks) or explicitly contrasting the two ref formats with use contexts.

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?

Use is implied by the single-task fetch verb and the two accepted ref formats. The internal note about workspace being auto-injected when ref is a key is helpful preconditioning, but there is no explicit 'use this instead of X' routing versus pm_search_tasks or pm_get_subtasks.

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