ghl_workflow_search

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

Annotations already cover the read-only/idempotent profile, and the description adds substantial context beyond them: limited availability with the exact 403 WORKFLOW_API_NOT_ENABLED_FOR_LOCATION error and the note that it is not a token/scope problem, plus dual rate limits (integration daily quota + 10s burst and a per-sub-account budget) with the explicit note that no Retry-After header is sent. That is exactly the failure-mode information an agent needs before calling.

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 core search paragraphs are well front-loaded and tight, but the header block carries a large amount of content irrelevant to a search call: the get-step-types -> build -> validate -> create -> publish pipeline and the log retention window (30/60 days) belong to other workflow tools. Roughly half the text does not earn its place for this specific operation.

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 correctly states the return shape is summaries only and explains how to get full definitions, and it covers paging, error mode and rate limits. Only the returned summary fields themselves are left unspecified, which is a minor gap given the schema documents the filter/sort inputs fully.

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 100% and the nested body schema already documents filters, operator/value typing, sort, limit, offset and searchAfter. The description reinforces the AND-filter semantics and the offset-vs-searchAfter exclusivity, but adds no format or syntax detail beyond what the schema states, so the baseline 3 applies.

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 states a specific verb and resource ("Search Workflows", "Find workflows in a sub-account by name, status, folder or timestamp") and explicitly scopes the output ("Returns summaries only") while naming the sibling needed for full data (Get Workflow Definition). An agent can distinguish this from ghl_workflow_list and ghl_workflow_get_definition without opening a 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 gives clear routing guidance (use this for summaries, pass an ID to Get Workflow Definition for the full definition) and concrete paging strategy (offset for the first few pages, then searchAfter; sending both is rejected). It also states the availability precondition and the 403 code. It does not explicitly contrast with the sibling ghl_workflow_list, which keeps it short of a 5.

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