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

Goes well beyond the readOnly/idempotent/non-destructive annotations: it discloses that private key blocks are rejected, that analysis is fully offline, that weak/SHA-1/expired/no-encryption-subkey keys are flagged, that a CRC-24 armor check is performed, and that each successful call costs $0.002 USDC via x402 on Solana with an equivalent HTTPS endpoint. The cost and rejection behavior are exactly the kind of details annotations cannot convey.

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 with the core action and the gpg comparison before the long enumeration of extracted fields. The dense feature list is long but each item is a real return-value category an agent might need; only the exhaustive algorithm roll-call (RSA/DSA/ElGamal/ECDSA/ECDH/EdDSA/...) borders on padding.

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 thoroughly: signature-derived dates, capability flags, split user IDs, preferred algorithms, armor CRC, and WKD URLs. Combined with the refusal and pricing disclosures, an agent has everything needed to call it and interpret the result.

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% and both parameters are documented in the schema, so the baseline is 3. The description adds useful context by naming the accepted formats (ASCII-armored or base64 binary) but never mentions the `now` parameter, so it does not improve on the schema's own explanation of expiry evaluation timing.

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 and resource ('Inspect an OpenPGP public key') and enumerates exactly what it extracts: fingerprints, key IDs, algorithms, expiry, capabilities, user IDs, WKD URLs. The 'way gpg --show-keys does, offline' framing plus the explicit key-format scope makes it unambiguously distinct from sibling parsers like ssh_key_info or x509_decode.

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 rather than stated: the key must be a public key block, private key blocks are refused, and the tool works offline. There is no explicit routing guidance such as 'use ssh_key_info for SSH keys' or 'use x509_decode for certificates', even though those siblings exist and an agent must pick between them. Adequate context, but no when/when-not framing against alternatives.

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