Omniseal

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

Adds substantial context beyond the annotations: results are binary MCP resources, the connector rejects payloads over 140,000 characters, and inputs must be actual bytes or reachable URLs. This overlaps with destructiveHint=false by confirming the original is preserved. It does not address auth for the private_seed beyond the schema's warning, but the disclosure is richer than typical.

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 short sentences, front-loaded with the primary action and effect, followed by the result-format constraint and the input requirement. No filler, though the limit sentence could be tightened into the result-format clause.

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 return-value burden and does so by stating results are binary MCP resources with a size ceiling. With only two well-documented required params, a nested sealed_file object, and annotations covering the safety profile, the remaining gap is the absence of any when-to-use routing.

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 sealed_file and private_seed are already fully documented with their oneOf constraints and warnings. The description only reinforces that inputs must be real bytes or reachable URLs, adding little beyond the schema's own 'Claude attachment IDs and local paths are not downloadable URLs' note. 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 specific verb and outcome: 'Return a new clean cover with the hidden payload removed; preserve the original sealed file.' This distinguishes it from seal_files (which creates the seal), verify_sealed_file (which checks it), and retrieve_secret_file (which extracts content). The terms 'cover' and 'hidden payload' are domain jargon, but the transformation is unambiguous.

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?

No guidance on when to choose this over verify_sealed_file or retrieve_secret_file, and no explicit preconditions beyond the input-shape note. The 'preserve the original' clause implies a non-mutating copy behavior, but the agent is never told the scenario that selects this tool versus its siblings.

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 readOnlyHint, idempotentHint, openWorldHint, and non-destructive behavior, so the safety profile is covered. The description adds real value beyond that: results come back as binary MCP resources and the connector rejects anything over a 140,000-character limit, which materially affects whether a call will succeed.

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 core action, then the return/size behavior, then the input constraint. Minimal waste, though the input-source sentence partially overlaps with the schema's own note about Claude attachments and local paths.

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 and a nested object parameter, the description does the important work of explaining the return shape (binary MCP resources) and the size ceiling that can cause failure. It omits error behavior for a wrong seed or corrupt sealed file, but the essentials for calling correctly are present.

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 the nested sealed_file object, its oneOf download_url/content_base64 constraint, and the private_seed warning are already documented in the schema. The description only restates the seed and input-source requirement, so the 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 specific verb and resource ('Recover the exact hidden file from an Omniseal sealed file using its private seed'), which is concrete and unambiguous. It does not explicitly name or contrast with siblings like seal_files, verify_sealed_file, or remove_hidden_file, but the action is distinct enough to route on.

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 by the requirement of a private seed and the note that inputs must be actual file bytes or reachable URLs, which implicitly excludes local paths and attachment IDs. There is no explicit when-to-use vs. when-to-use-an-alternative guidance and no stated prerequisites beyond the seed.

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 cover the safety profile (readOnly=false, destructive=false, idempotent=true), and the description adds real context beyond them: originals are not overwritten, results come back as binary MCP resources, and there is a 140,000-character result-size ceiling. The size limit is exactly the kind of operational trait an agent needs and annotations cannot express.

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, each carrying distinct information (purpose, output medium/size limit, input requirement), with the core action front-loaded. Slightly dense but no wasted clauses.

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 and three required parameters including nested file objects, the description still covers the return type (new sealed file as a binary resource), the key size caveat, and acceptable input forms. Only the routing-vs-siblings guidance is missing.

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 the nested cover_file/secret_file oneOf structures and private_seed guidance are already documented. The description's note that inputs require actual file bytes or reachable URLs is useful but largely restates what the schema descriptions already say, 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 precise verb+resource ('Conceal a secret file inside a cover file') plus the output ('returning a new sealed file'). This clearly separates it from siblings like remove_hidden_file, retrieve_secret_file and verify_sealed_file without needing to name them.

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 supplies constraints (no overwriting originals, 140,000-character result limit, inputs need real bytes or reachable URLs) but never states when to prefer this tool over the sibling seal/retrieve/verify operations. Usage is implied rather than guided.

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 cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower, and the description still adds real context: results come back as binary MCP resources and the connector rejects payloads over 140,000 characters. That size cap is exactly the kind of operational constraint an agent would otherwise discover only by failing.

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 short sentences, all front-loaded: purpose first, then output/limit behavior, then input requirement. No filler or redundancy.

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 bears the burden of explaining returns, and it discloses the binary-resource result type and the size ceiling. It stops short of describing what the verification verdict itself contains (tamper/no-tamper fields), which is a minor remaining gap for a single-parameter tool.

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 nested object already documents file_name, mime_type, download_url, content_base64 and the one-of requirement, plus the note that attachment IDs and local paths are not valid URLs. The description's 'actual file bytes or reachable URLs' restates that constraint without adding syntax or format detail, 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 specific verb and resource: checking an Omniseal sealed file for tampering signs. An agent can distinguish this from seal_files (creation) and retrieve/remove siblings, though the description never names an alternative directly.

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?

Gives an input precondition ('Inputs require actual file bytes or reachable URLs'), which is useful usage guidance, but never says when to reach for this tool versus the sibling seal/retrieve/remove operations or what tier of file it applies to. Usage is implied rather than stated.

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