pl_search

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

Despite annotations already declaring readOnly/openWorld/idempotent behavior, the description adds substantial context: parameter normalization (0- vs 1-based pages), clamping of limit, verbatim merging of extra filters, and a comprehensive list of error codes. It discloses deprecated page_number alias and source-specific behaviors beyond the structured hints.

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 front-loaded with the purpose sentence, then systematically covers parameter behavior in a compact block, followed by an error list. Every sentence carries operational value, and the length is appropriate for the tool's complexity.

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 parameter semantics, error handling, source adapters, and cross-references to sibling tools (pl_list_sources and pl_get_document) for additional context. An output schema exists, so return-value details are not needed in the description; the provided information is complete for a tool of this complexity.

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?

With 0% parameter documentation in the schema, the description compensates fully by explaining date format, page numbering, limit clamping, extra native filters, and the deprecated page_number alias. Even though query and source are not individually defined, their meanings are self-evident from the schema and the first sentence.

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 'Unified search across any registered source (SAOS, NSA, ISAP, EUREKA, KIO, UODO...),' using a specific verb and resource scope. It clearly distinguishes itself from siblings like pl_get_document and pl_list_sources by focusing on search across sources.

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 establishes when to use the tool ('Unified search across any registered source') and cross-references pl_list_sources for native parameter names, but it does not explicitly state when to avoid this tool or name direct alternatives beyond the sibling tool names. This is clear context without explicit exclusions.

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