Hash (MD5 / SHA)

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

Annotations already declare readOnlyHint, idempotentHint and a closed-world scope, so the safety profile is covered. The description adds genuinely useful context about which checksum formats are accepted (hex in any case/spacing, 'SHA256 (file) = …' lines, base64) and that the tool reports which algorithm matched. It says nothing, however, about how the hash results themselves are returned (one per algorithm? a list? keyed by name?), which is meaningful for a compute tool with no output schema.

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 dense sentence front-loads the algorithms and input modes, followed by a short reference URL. It is efficient with no filler, though the one long sentence packs four distinct capabilities together rather than separating them for scanning.

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 zero required parameters, six optional inputs, and no output schema, the description covers inputs well but leaves the response shape undocumented — the agent cannot tell whether it receives a single object keyed by algorithm or one field per algorithm, nor what a checksum mismatch returns. Adequate to invoke correctly, incomplete for interpreting results.

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 83%, giving a baseline of 3, but the description adds real value: the schema exposes no algorithm selector, so the description is the only place stating that MD5/SHA-1/SHA-256/SHA-512 are all computed, and it clarifies 'path or base64' disjunction for the file parameter plus the checksum-format tolerance for `expected`. Minor mismatch: `hmacAlgorithm`'s SHA-384 enum value is never mentioned in the prose.

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 ('Compute MD5, SHA-1, SHA-256 and SHA-512') plus the three input modes (text, file path, base64) and the optional HMAC and checksum-verification behaviors in one pass. An agent can distinguish it from crypto_file_encrypt, base64_encode, or ai_file_identify without opening any 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 'text or a file (path or base64)' phrasing tells the agent which input mode to pick, and 'optionally an HMAC with a key' plus 'check against an expected checksum' signal when the extra behaviors apply. It stops short of naming an alternative tool or an explicit when-not-to-use case.

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