Compute SHA-256, SHA-384, SHA-512, SHA-1, and MD5 hashes or Base64/Base64URL encodings of text locally to verify data integrity.
Compute deterministic cryptographic hashes (sha256, sha384, sha512, sha1, md5) and Base64 / Base64URL encodings of input text locally.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Input text string to hash and encode | |
| algorithm | No | Hash algorithm to use (default: 'sha256') |
Changes observed during successful MCP inspections.
v1.3.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false, idempotentHint=true and destructiveHint=false, so safety and locality are covered. The description's 'deterministic' and 'locally' largely restate idempotentHint and openWorldHint rather than adding new behavior, and it says nothing about output format (hex vs raw, padding) or whether Base64 output requires an extra request.
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?
A single well-formed sentence with the action, algorithm enumeration and execution scope front-loaded; no filler or redundant 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?
For a pure-compute tool with rich annotations the description is nearly adequate, but with no output schema it never states what comes back (hex digest string, encoding case, padding), and the unprompted Base64/Base64URL claim leaves an unanswered question about how that output is obtained.
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% with only two parameters, so the schema already documents 'text' and the algorithm enum with its default. The description's algorithm list duplicates the enum, and its Base64/Base64URL mention implies an output-format choice that no parameter exposes, which could mislead rather than clarify.
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 gives a specific verb (compute) plus the resources (cryptographic hashes, Base64/Base64URL encodings) and names the exact algorithms, which cleanly separates it from siblings like castov_jwt_decode or castov_scan_secrets. It stops short of explicitly naming any sibling or stating a boundary against them, and the Base64/Base64URL claim has no corresponding parameter in the schema, which slightly muddies the scope.
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 only implied: an agent can infer this is the tool for hashing arbitrary text rather than decoding JWTs or scanning secrets. There is no explicit when-to-use statement, no exclusions, and no mention of when a sibling such as castov_jwt_decode would be the better pick.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.