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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description still adds substantive behavior the annotations cannot convey: PEM is silently converted to OpenSSH format, private keys are rejected outright, fingerprints are emitted exactly as ssh-keygen prints them, and weak keys (DSA, short RSA) are flagged. It also discloses the commercial model — $0.002 USDC per successful call via x402 on Solana — plus a direct HTTPS endpoint, which is exactly the kind of cost/transport context an agent needs before invoking.

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?

Front-loaded correctly: the core verb and resource come first, followed by capability detail, then commercial/transport terms. It is dense with a long parenthetical chain (the certificate-decode list especially), which costs some readability, but essentially no sentence is filler given the breadth of behavior being disclosed.

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?

There is no output schema, so the description carries the return-value burden — and it does so thoroughly by listing every field class returned for both keys and certificates. Remaining gaps are minor: no statement of error behavior for unparseable input, no mention of the input size cap, and no note on how duplicate detection is reported.

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?

With a single parameter at 100% schema description coverage, the baseline is 3, and the description largely restates what the schema already says about line-per-key vs. RFC 4716/PEM block formats. It adds no guidance on the 500,000-character limit, multi-key behavior, or what happens on a malformed line, so it does not exceed the schema baseline.

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?

Opens with a specific verb+resource pair ('Inspect SSH public keys and OpenSSH certificates') and then enumerates the exact outputs an agent can expect (type, size/curve, fingerprints, options, FIDO, duplicate detection, strength verdict, certificate decoding). This is clearly distinguishable from the neighboring pgp_key_info and x509_decode tools 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?

It spells out the accepted input sources (authorized_keys, known_hosts, .pub, RFC 4716, PEM) and gives one explicit exclusion: private keys are refused. It does not, however, route the agent to alternatives such as pgp_key_info for PGP keys or x509_decode for X.509 certs, so the 'when not to use this' side is only partially covered.

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