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

With no annotations provided, the description carries full behavioral transparency responsibility. It states 'Deterministic and read-only: missing facts are reported, never guessed,' which clearly communicates that the tool never fabricates data and is safe for read-only use. It also notes the output is source-linked, adding helpful behavior context, though it omits details like rate limits or error handling.

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 two sentences with no wasted words, front-loading the core action and data sources, followed by a concise behavioral note. It earns its length by providing purpose and safety in a compact form, though it could have used the space to address some parameter 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?

Given the tool's complexity (16 parameters, no output schema, no annotations), the description is insufficiently complete. It does not explain the structure of the 'answer bundle,' how parameters combine, what fallback_mode values mean, or the output format. An agent would need deep inference from parameter names and sibling tool behavior to use it correctly.

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 low at 50% (8 of 16 parameters documented). The description adds no parameter-level detail and does not compensate for undocumented parameters such as year, location, min_area_m2, max_area_m2, or price_limit. It only gives high-level context about composing from public data, leaving the agent to guess meanings of the other half of the parameters.

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 states a specific verb+resource: 'Compose a compact, source-linked answer bundle' from the structured service catalog, cennik, service-area evidence, and realization portfolio. The title adds that it resolves renovation questions, and this clearly distinguishes it from sibling getters like get_prices or get_realizations, which return single data types rather than a composed answer.

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 implies this tool is for answering natural-language renovation questions by composing multiple source types, but it never explicitly says when to use ask_oleba versus a sibling getter, nor does it provide exclusions or conditions. An agent can infer the usage context from 'resolve a renovation question,' but explicit routing guidance is absent.

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