Aigine Redact

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

Annotations already tell the agent this is a non-read-only, non-idempotent, non-destructive, closed-world call. The description adds real context beyond that: the link is temporary with zero data retention, the data stays in the EU, the widget is inline, and a URL is returned. It still omits link expiry duration, size limits, and what happens if the widget cannot be rendered.

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?

One dense sentence that front-loads the primary action and puts the return value immediately after. The 'AND' clause makes it slightly run-on, and parenthetical '(MCP Apps)' plus repeated 'EU' phrasing could be tightened, but no sentence is wasted.

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 no output schema, the description carries the burden of explaining the return value, and it does name upload_url and its temporary/zero-retention nature. However, it leaves out practical details an agent would need, such as link lifetime, file size limits, and fallback behavior for non-MCP-Apps clients. Adequate but with clear gaps for a tool whose only output is a transient URL.

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 tool takes zero parameters, so there is nothing for the description to clarify and the baseline is 4. The description correctly does not invent parameter information and instead spends its words on output and behavior.

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 uses a specific verb ('Opens') with two concrete deliverables: an inline drag-and-drop widget in MCP Apps clients and a temporary EU upload URL (upload_url). It clearly states accepted file types (PDF, DOCX, PPTX, image) and the destination (Aigine in the EU). It does not name or contrast with the siblings fetch_reviewed_document or propose_masking, but their purposes are far enough apart that confusion is unlikely.

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 rather than stated: use it when a user needs to upload a document to Aigine in the EU. The phrase 'supporting chat clients (MCP Apps)' hints at an environment constraint but does not say what to do when the client does not support the widget. There are no explicit when-not conditions or references to alternatives.

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?

Goes well beyond the annotations: the URL is temporary, the document is deleted from the processing server immediately after, and the call requires a completed human review. The one unresolved tension is that this deletion is a destructive-ish side effect while destructiveHint=false (readOnlyHint=false and openWorldHint=true are consistent); that should be reconciled, but it is disclosed rather than hidden, so no outright contradiction.

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?

One dense sentence that front-loads the most important constraint (human-only) before the mechanics. It is efficient, though the nested parenthetical about clicking 'Open redacted PDF' in the browser slightly interrupts the flow.

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 one-parameter tool with no output schema, the description still covers the return value (temporary download_url), the lifecycle side effect (immediate deletion), and the caller precondition. An agent has everything needed to decide whether it may call this at all and what happens afterward.

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?

There is a single parameter with 100% schema description coverage, and the schema already explains that doc_id comes from propose_masking with status 'awaiting_review'. The description only restates 'call this tool with doc_id' and adds no format, validation, or error-handling nuance, 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?

States a concrete verb and resource plus its output: 'call this tool with doc_id to get a temporary download_url for the masked PDF'. It also names the side effect (deletion from the processing server) and the upstream step (propose_masking/review_url), so the agent can place it in the workflow 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?

Explicitly opens with the exclusion 'INTERACTIVE HUMAN MODE ONLY (autonomous agents must never call this tool)' and gives the precise precondition: a human has finished validating at review_url and clicked 'Redact'. It even covers the case where the tool is unnecessary, since the human can open the redacted PDF directly in the browser.

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 openWorldHint=true, readOnlyHint=false, and non-idempotent behavior. The description adds genuinely valuable traits annotations cannot express: EU-only processing, an 'irreversible/flattened' output PDF, zero data retention, and an outbound-network prerequisite for /mcp/api/upload. However, it omits failure modes, size limits beyond the 45 KB base64 note, and what the caller receives back, which matters for a non-idempotent mutation.

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 core purpose is front-loaded in one dense sentence, then the operational rules are numbered and scannable. It is on the long side and the final URLs plus explicit UI click-path instructions ('clicking Redact then Open redacted PDF') are borderline excess, but every rule maps to a real fork in behavior.

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 six-parameter, zero-required, non-idempotent operation with no output schema, the description covers ingestion paths, upload prerequisites, policy defaults, and the human-review branch. An agent has everything needed to pick an input mode and invoke the tool correctly without further discovery.

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 every parameter is already documented at the field level, establishing a baseline of 3. The description adds procedural meaning the schema cannot — the ordering constraint that upload_id comes from POST /mcp/api/upload, and that file_url/document_base64 are substitute ingestion paths — but it does not clarify policy semantics or mutual exclusivity of the input sources beyond what the schema states.

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 sentence names a specific verb (identify and mask), two concrete domains (GDPR direct/indirect/Art. 9 and OSL/trade secrets), and the supported file types. It is immediately distinguishable from create_upload_link and fetch_reviewed_document, which are upload and retrieval helpers rather than the masking operation itself.

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?

Three explicit scenarios are enumerated (autonomous agents, chat attachments, interactive human chat), each with a prescribed action and, where relevant, the fallback. The sibling create_upload_link is named with the exact condition that triggers it, so routing decisions are fully determined.

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