Search jobs (server-side table query: paging, sorting, filters)

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 genuinely non-redundant context: that a read-only query is issued as a POST with filters in the body, which keys come back (draw, recordsTotal, recordsFiltered, data, meta, table_id, settings), and that the shape was inferred from observed web-app traffic and should be verified. That last point is a valuable trust caveat an agent would otherwise miss.

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 dominated by a mechanical, repetitive enumeration of columns[0] through columns[6] that is cut off mid-pattern ('columns[6][searchable]'), adding noise rather than structure. The useful facts (method, return keys, inference caveat) are buried after this list and the enumeration should have been summarized as a pattern.

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 supplies the response key list, HTTP method, param-vs-body split, and a provenance/reliability caveat, which is close to everything an agent needs. The one gap is that the column-index semantics (what each index corresponds to) are never explained, leaving the columnar filter payload opaque.

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% but the top-level body parameter is a free-form object with no meaningful field documentation, so the description's enumeration of observed body keys (draw, columns[n][data|name|searchable|orderable|search][value|regex]) is what actually tells the agent how to build the request. It also clarifies that job_id is a query param while filters go in the body.

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 and resource ('Search jobs') plus the mechanism ('server-side table query: paging, sorting, filters'), which tells an agent this is the DataTables-style paged query. However, it does not distinguish itself from closely named siblings such as singleops_read_search_jobs_report, singleops_read_search_jobs_invoices, or singleops_read_search_jobs_progress_billing, so the agent cannot be certain which job-search variant to pick.

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?

Usage is only implied by the 'server-side table query' framing and the endpoint hint (POST /jobs/jobs_datatable). There is no explicit statement of when to prefer this over the other search_jobs_* siblings, nor any prerequisite or exclusion. The 'confirm results' caveat is a reliability warning rather than selection guidance.

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