pdb_search

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

With no annotations supplied, the description carries the full burden; it does disclose that the operation is read-only and that results are paged because 'GIMP commonly exposes hundreds of procedures,' which is genuinely useful scale context. It stops short of stating the regex dialect accepted (GIMP PDB patterns vs. general regex), the shape of each returned record, or the error behavior for an invalid pattern.

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 clause, followed by usage rule, field list, and paging caveat in a logical order with no filler. The parenthetical '(read-only discovery)' and the paging sentence both carry weight; only the multi-line field enumeration is slightly dense.

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?

There is no output schema, so the agent must infer what a result record contains, and the description never describes the returned entries beyond saying they are paged. For a 4-parameter discovery tool feeding into pdb_describe/pdb_run, it covers the call path adequately but leaves the return contract underspecified.

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, and it largely does: it enumerates the valid `field` values (name, blurb, help, help_id, authors, copyright, date, proc_type), explains that `pattern` is a regex, and notes that results are paged, which justifies `limit` and `offset`. It still does not state default values or the maximum permitted `limit`, so a small gap remains.

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 procedures installed in this GIMP instance') plus an explicit scope qualifier ('read-only discovery'). An agent can immediately distinguish this metadata-discovery tool from the focused siblings like resize_canvas or apply_noise that perform actual operations.

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?

Gives a clear selection rule — 'Use this when a focused tool does not cover the operation' — and an explicit follow-up step ('call pdb_describe before execution'), which is exactly the workflow guidance an agent needs. It does not, however, differentiate from the other discovery siblings such as gegl_list_operations or gegl_list_filters, leaving ambiguity about which catalog to query.

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