search_tickets

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

Beyond the readOnlyHint annotation, the description discloses two genuinely non-obvious behaviors: the automatic default field set with Queue/Owner expanded to names, and the fact that fields/subfields replace rather than add to defaults. It also reveals the Status meta-value semantics (__Active__/__Inactive__), which an agent could not infer from the schema, and the description's read-only framing is consistent with the readOnlyHint annotation.

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 purpose is front-loaded in the first sentence, immediately followed by the most critical warning (consult the grammar). Each remaining sentence covers a distinct non-obvious point — meta-values, examples, default field semantics — with no filler, though the description is on the longer side for an API tool.

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?

The description covers the highest-risk area thoroughly: the query language's non-obvious syntax, the Status meta-value gotcha, and the default-field replacement behavior. With no output schema present, it leaves return-format details unstated, but pagination and field semantics are well documented in the schema, so the coverage is strong overall.

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%, so the baseline is 3, but the description adds real value above the schema: it teaches the TicketSQL syntax rather than just labeling the query parameter, provides concrete examples ('Queue = 'General' AND Owner = 'Nobody''), and explains when to pass fields or subfields (only when the default set is insufficient). This goes beyond the schema's plain 'TicketSQL query string' and 'Comma-separated fields' descriptions.

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 opening sentence 'Search for tickets using RT's TicketSQL query language' names a specific verb, resource, and method, so the tool's job is unambiguous. This clearly distinguishes it from single-ticket retrieval siblings like get_ticket and get_ticket_history, which an agent can tell apart at a glance.

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?

The description explicitly names get_ticketsql_grammar as a prerequisite ('consult get_ticketsql_grammar before writing any query involving Status, date conditions, custom fields, or special values'), which is concrete when-to-first-do guidance. However, it never states when to prefer a sibling such as get_ticket over this search tool, so there are no explicit exclusions.

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