anonymize_text

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it replaces PII with pseudonyms, generates a UUID for later deanonymization (with a strong warning to preserve it), and returns entity counts. It also explains the impact of the 'depth' parameter on detection methods. While it covers core functionality, it lacks details on error handling or performance characteristics like rate limits.

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 and appropriately sized, with a clear purpose statement followed by sections for Args and Returns. Each sentence adds value, such as explaining parameter options and emphasizing the importance of the mapping_id. It could be slightly more concise by integrating the 'depth' explanation more tightly, but overall it is efficient and front-loaded.

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 (PII anonymization with multiple detection methods) and the presence of an output schema (which details return values like anonymized_text and mapping_id), the description is complete enough. It covers purpose, parameters, usage context, and key behaviors without redundancy. The output schema handles return value specifics, so the description appropriately focuses on operational guidance.

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 fully. It does so by explaining both parameters in detail: 'text' is described as the text to anonymize with examples (contract, judgment, complaint), and 'depth' is explained with clear semantics for 'thorough' (all layers: regex + NameTag NER + BERT + dictionary) and 'quick' (only regex patterns). This adds significant meaning beyond the basic schema.

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 clearly states the tool's purpose with specific verbs and resources: 'Anonymizuje český text — nahradí PII pseudonymy jako [OSOBA_1], [IČO_1]' (Anonymizes Czech text — replaces PII with pseudonyms like [PERSON_1], [ID_1]). It distinguishes itself from sibling tools like 'deanonymize' by focusing on the anonymization process rather than reversal or file handling.

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 clear context for when to use the tool: for anonymizing Czech text in documents like contracts, judgments, or complaints. It also offers guidance on the 'depth' parameter with recommendations ('thorough' is recommended). However, it does not explicitly state when not to use this tool or compare it to alternatives like 'anonymize_file' for file-based processing.

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