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

Goes well beyond the readOnly/idempotent/openWorld annotations: it discloses that no LLM call, API key or quota debit occurs, that text leaves for neuroslop.net (external network egress), that the tool abstains when evidence is thin, and that the 0–100 score is not an AI-authorship probability. Those are exactly the behavioral and interpretive facts an agent needs.

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?

Short, dense and front-loaded: cost/mechanism first, then return shape, coverage caveat, then the misinterpretation warning. Every sentence carries distinct information with no repetition.

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 an output schema present, the description needn't detail return values, and it still characterizes them at a high level. Cost, privacy egress, language coverage and score interpretation are all covered, leaving nothing an agent needs before calling.

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% and the single 'text' parameter is fully documented in-schema, so the baseline applies. The description adds only the indirect hint that language is detected automatically and that the text is transmitted externally, not new semantics for the parameter itself.

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+resource: deterministic style analysis of text, with the returned artifacts named (style markers, applicability, abstention). It never names the sibling tools humanize/clean, so the agent must infer that this one only analyzes rather than rewrites.

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?

Usage is implied (analysis, not transformation) and the cost-free nature encourages calling it, but there is no explicit 'use this when… / use neuroslop_humanize instead when…' routing. The RU/EN coverage note is the only near-guidance, and it concerns limits rather than tool selection.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower; the description still adds real context: local/no-API-key execution, that the output includes change counts, that matches may be legitimate text, and a warning to review before overwriting. It does not contradict any annotation.

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?

Five short sentences, front-loaded with the action and scope, with no redundancy; the caution and the negative disambiguation each carry distinct information.

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 explained, and the annotations carry the safety profile; the description supplies the local-execution fact and the review-before-replacing warning. Only marginal gaps remain, such as handling of text that exceeds limits or yields no changes.

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?

With a single parameter at 100% schema coverage, the schema already documents the input and the 20,000 UTF-16 code-unit limit. The description adds no format or content guidance (e.g. what counts as an 'invisible character') beyond the schema, so baseline 3 applies.

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 and resource ('Locally normalize invisible characters, unusual spaces and Latin lookalikes from Cyrillic/Greek') and explicitly rules out a neighboring concern ('This is not authorship detection'), which separates it from neuroslop_check. An agent can distinguish it from its siblings without opening the schema.

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 usage through a caution ('review changes before replacing the original') but never states when to pick this over neuroslop_check or neuroslop_humanize, nor any prerequisites beyond 'no network or API key'. The routing decision is left to inference.

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

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

Annotations only flag openWorld=true and idempotentHint=false; the description goes well beyond them by disclosing that text is transmitted to neuroslop.net and third-party generation providers, that a call consumes paid quota, that local edits can return spent=0, and that replay depends on the provider's receipt retention. The warning that 'a missing receipt or unknown delivery is not permission to start another paid run' is exactly the kind of non-obvious side-effect guidance an agent needs.

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 purpose is front-loaded in the first clause, but the remainder is a dense run-on chain of caveats with no separation between cost, privacy, idempotency, and score-availability concerns. Phrases like 'Scores may be independently unavailable' are cryptic and cost the agent parse time without clear payoff.

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 paid, non-idempotent, open-world mutation with an output schema, the description covers the critical gaps: spend approval, external data transmission, and retry/receipt semantics. The only shortfall is the unexplained reference to 'scores' and the absence of any sibling comparison.

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 100%, so lang, mode, tier, text, and requestId are already documented, which sets the baseline at 3. The description reinforces requestId reuse semantics ('only for the same operation') but adds nothing about the other four parameters beyond the schema text.

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 opening clause, 'Request editorial rewriting with an API key and user approval to spend quota,' names a specific verb (rewrite) and resource (text), so an agent knows this is a paid text-rewriting call. However, it never explains what 'humanize' means in relation to the siblings neuroslop_check and neuroslop_clean, nor how this rewrite differs from a cleanup pass.

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 gives concrete preconditions for calling (API key plus user approval to spend quota) and a retry rule for requestId, which is real usage guidance. It stops short of telling the agent when to pick this tool over neuroslop_clean or neuroslop_check, so selection is left implied.

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