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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered; the description adds genuine extra context: date filters key off the displayed start date (including overnight shifts), and shift IDs are unstable after archive/bulk edit, which is a real gotcha. Minor inconsistency: it says "next_offset" while the schema parameter is "offset", which could confuse pagination.

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?

Four short sentences, front-loaded with the core purpose and pagination, then the two non-obvious caveats. Dense and waste-free, though the mixing of pagination, date semantics, and ID instability in one block reads as a list of caveats rather than a structured flow.

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 and 0% schema coverage across 7 params, the description covers the trickiest parts (date filtering, pagination, ID instability, historical worklogs) but leaves filter parameters unexplained — an agent cannot tell whether owner/jobtypes/location expect IDs or names. Adequate but with clear gaps for a filter-heavy list tool.

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 0%, so the description must carry the burden, and it explains the date filter semantics (start_date/end_date apply to displayed start date) and pagination via offset/next_offset. It says nothing about owner, jobtypes, location, or limit (max 50), leaving four of seven parameters with no semantic guidance.

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?

"One page of upcoming shifts for the selected account" states a clear verb (list) and resource (shifts) with page scope, which implicitly separates it from smartplan_get_shift (single shift) and the list_* siblings. It never names a sibling explicitly, so the differentiation is inferred rather than stated.

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?

"continue with next_offset" gives concrete pagination guidance, which is real usage direction. However there is no explicit when-to-use/when-not-to-use guidance versus smartplan_get_shift or the other list_* tools; the mention that "worklogs are historical records" only hints at an alternative.

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