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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds meaningful non-schema context: the search is free and works without an account, and results come back as a single numbered contact sheet, which tells the agent what to expect.

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?

Dense but front-loaded, with the core routing rule first and the workflow/costing caveats after. Every sentence carries information, though the Blueprint cross-reference sentence is long and slightly packed.

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 describes the return shape ('one numbered contact sheet') and gives ordering/mapping notes for reuse in Blueprint. It is nearly complete for a search tool, missing only clarifications for the un-described filter parameters.

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 carry the load. It partially does: it enumerates acceptable 'kind' values and gives real guidance for 'q' (German or English, short concrete English nouns match best). However, limit, orientation, and transparent are entirely unexplained, leaving half the parameters undocumented.

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 (browse/search) plus the resource (Picorn's own picture library) and enumerates the content kinds it covers. It clearly distinguishes itself from siblings like picorn_search_icons and picorn_generate_image by scoping to the library and naming the generative alternative explicitly.

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?

Leads with 'LIBRARY FIRST' and states the when-not condition: generating costs credits and is 'the exception: only when nothing here fits.' It also prescribes the follow-up workflow into picorn_blueprint_compile with the exact syntax to use.

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