compare_acts

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

With no annotations present, the description carries the full behavioral burden. It clearly states what the tool compares, that it identifies differences and common elements, and that it does not require prior content loading. It does not explicitly label the operation as read-only, but comparing metadata strongly implies a non-mutating action, and the output schema covers return structure.

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 well-structured: summary line, detailed scope, usage guidance, exclusions, and examples. It is front-loaded with the most important information. The five examples are somewhat repetitive, but they demonstrate diverse comparison scenarios, so they earn their place without excessive bloat.

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?

For a two-parameter comparison tool with an output schema, the description is complete: it states purpose, inputs, scope, prerequisites, exclusions, and examples. An agent has everything needed to select and invoke this tool correctly and to avoid confusing it with content-reading siblings.

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?

The input schema already documents both parameters with format and examples, achieving 100% coverage. The description adds use-case examples that pair eli_a and eli_b in meaningful ways (e.g., versions, different publishers), but this is illustrative rather than necessary parameter semantics. Baseline 3 is appropriate since the schema does the heavy lifting.

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 a specific verb and resource: 'Porównaj metadane dwóch aktów prawnych' (compare metadata of two legal acts). It enumerates the exact metadata dimensions (titles, types, statuses, dates, keywords) and explicitly differentiates itself from content comparison via read_act_content, so the tool's role among siblings is unambiguous.

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 provides explicit 'Kiedy użyć' and 'Kiedy NIE używać' sections, directing the agent to read_act_content for content comparison instead. It also notes that loading content beforehand is not required, which removes a possible mistaken prerequisite.

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