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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses that the call is stateless, capped at 32 KB and 60 RPM, supports a '?demo=true' free path or L402 payment of 15 sats, and returns HTTP 400 on invalid input. Rate limits, auth/billing paths and error behavior are exactly the operational context annotations do not carry.

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?

Three sentences, front-loaded with the operation list before usage routing and then operational constraints — the ordering matches how an agent decides. The final sentence is dense with limits, auth and error codes, but each clause is load-bearing rather than filler.

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?

An output schema exists, so return values need not be described, and the description supplies everything else material for a stateless 2-parameter tool: size cap, throughput cap, payment path and failure mode. The only completeness defect is the default-value conflict, which undercuts an otherwise thorough definition.

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 coverage is 100%, so a 3 would be the baseline, but the description asserts 'normalization_mode' defaults to 'exact_match' while the schema explicitly states it defaults to 'case_insensitive_trim'. For an agent choosing whether to pass the parameter, that conflicting statement is actively misleading and worse than silence.

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 first sentence names four specific operations (dedupe, Unicode whitespace normalization, HTML/control stripping, tabular/JSON canonicalization) against concrete inputs (lines, records, CSV rows, JSON arrays). It is unambiguously distinguishable from nearby siblings like extract_clean_markdown or heal_malformed_json.

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?

It gives explicit trigger conditions ('noisy scraped lists, CSV rows, or duplicate log lines before indexing or analysis') and names the alternative plus the condition that selects it ('for extracting typed JSON fields from free-form prose paragraphs, use extract_structured_json_entities').

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