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

With readOnlyHint=true and openWorldHint=false already declared, the description adds genuine non-obvious context: nothing is stored or logged, it is pure computation, and it has no cost. That is exactly the kind of extra assurance worth adding on top of annotations, though the default algorithm when omitted is left undisclosed.

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 what it computes, then the safety note, then the cost note. No filler and nothing repeats the schema.

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 small, single-purpose pure-compute tool with no output schema, the description covers inputs, output encoding, safety, and cost. Only the default algorithm behavior is missing, which is a minor but real gap for correct invocation.

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 0% and there are no enums, so the description has to carry the load — and it does, naming all three parameters' roles and enumerating the valid algorithm values (sha256, sha512) plus the hex output format, which the schema omits entirely. The one gap is that the default/optional status of 'algorithm' is never stated.

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 an HMAC ... of a message with a key') plus the supported algorithms and output encoding (sha256/sha512, hex), which cleanly separates it from the plain-hash sibling bursia_hash. It does not explicitly name that sibling, so differentiation is inferential rather than stated.

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?

'Use test keys only' is a real usage constraint, and 'pure computation, free' sets expectations, but neither sentence tells the agent when to pick HMAC over bursia_hash or bursia_base64. Usage is implied by the verb rather than explicitly routed.

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