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

Annotations only supply readOnlyHint=true, and the description adds real behavioral detail beyond that: a 93-day ceiling on the query window, the fact that free-text leave notes are omitted from results, and that includeDeleted defaults to true upstream. These are exactly the kind of constraints an agent cannot recover from annotations or schema. Return shape and pagination are still unstated.

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?

It is very short and the purpose clause leads, so nothing is blatantly wasted. But the telegram style ('Max93days here', 'includeDeleted defaults true upstream') compresses several distinct facts into unpunctuated fragments, making it slower to parse than a slightly longer, structured sentence would be.

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 wisely notes that free-text notes are omitted from results, and it flags the range cap and includeDeleted default. Still missing for a 5-parameter filtered list tool: the accepted date format for required from/to, and any indication of result ordering or size limits.

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 0% for the top-level fields, so the description has to carry the load; it does explain overlap behavior for from/to, the includeDeleted default, and that employeeIDs/typeIDs act as filters. But the critical date format for from/to is never given, and the phrase 'repeated employeeIDs/typeIDs filters' is ambiguous (OR vs AND across repeated values) against a schema that already declares them as arrays.

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 with scope: read leave overlapping a from/to range, explicitly including leave that starts before 'from'. That overlap semantics distinguishes it from workfeed_get_leave (single record) implicitly, but the description never names that sibling or says it returns a collection.

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?

Useful implied guidance comes from 'Read any leave overlapping from/to, including leave beginning before the range', which tells the agent this is a range query rather than a point lookup. However, there is no explicit 'use this instead of get_leave when...' or any exclusion, so the agent must infer the routing from sibling names.

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