Recent Changes

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, so the agent knows it's a safe read operation. The description adds valuable behavioral context: it is keyset-based (so no performance degradation with depth) and it explains the sync pattern with server_time to be passed as `since` on the next call. This goes beyond the annotations and helps the agent understand the tool's streaming behavior, though it doesn't describe any edge cases like empty results or error handling.

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?

The description is concise but packs a lot: purpose, usage, keyset note, parameter bullets, and return format. It opens with the purpose, then usage, then technical detail. Bullet points for parameters are clear. The only minor inefficiency is the mention of 'keyset-based' and 'depth doesn't degrade performance' which could be folded, but it's acceptable. It's front-loaded and not verbose.

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 sync tool, the description covers the essential flow: how to start (since), how to paginate (keyset, server_time), what is returned (data, pagination, sync.server_time), and the pattern for the next call. It even mentions an alternative. The output schema is said to exist but not shown; the description summarizes the key fields. The only gap is the undocumented `offset` parameter, which could confuse an agent. Overall, it's nearly complete for its purpose.

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%, so the description must compensate for all parameters. It explains `since` (ISO 8601 timestamp with example) and `limit` (max 1000 per page), which is helpful. However, it omits any explanation for `offset`, which appears in the schema as a parameter with default 0. Given the keyset-based nature, offset is likely irrelevant or discouraged, but the description doesn't clarify its purpose or whether it should be used. This partial coverage earns a 3.

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 opens with a specific verb and resource ('List opportunities added or updated since a timestamp') and immediately distinguishes itself from pagination-based searches. It clearly names the alternative (search_opportunities) and the purpose (incremental sync), so an agent can tell it apart from sibling list tools without inspecting schemas.

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 explicitly instructs when to use this tool: 'Use this for incremental sync instead of paginating through search results.' This is a direct usage directive that contrasts with the pagination-filled search_opportunities. The description also implies when not to use it (when you need full result sets) by highlighting the incremental sync advantage.

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