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

The annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description goes further by disclosing the input constraint (regular file, ≤32 MiB) and the important epistemic limitation of a successful match, which the annotations do not 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?

Two sentences, front-loaded with what the tool does, and the second sentence is a substantive caveat rather than filler. No redundancy with the title or 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 three-parameter read-only tool with full schema coverage and complete annotations, the description supplies the needed behavioral context; there is no output schema, so return-value explanation is not owed. It could mention what is returned when expected is supplied (e.g., match/mismatch), but the gap is minor.

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%, so all three parameters (path, expected, algorithm) are already documented in the schema, including the accepted expected-digest formats and the enum values. The description only restates the algorithm options and the size limit, adding no syntax or format detail beyond the schema. Baseline 3 applies.

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+resource ('Computes the SHA-256 or SHA-512 digest of a local file') plus the optional comparison behavior, and scopes the input (regular file, up to 32 MiB). Nothing about it could be confused with the redaction, secret-scanning, or webhook siblings.

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 description implies the use case (hashing a file and optionally checking it against an expected digest) and adds a trust caveat about what a match proves, but it never states when to reach for this tool versus alternatives or what the prerequisites are. Usage is inferable rather than explicit.

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

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

Goes far beyond the readOnly/idempotent annotations: it states the tool holds no key, never checks the signature, cannot confirm the token is genuine, masks secret-looking claim names, and flags specific risk classes (alg none, HMAC, missing exp, jku/jwk/x5u). It also discloses the side effect that claims end up in the model context.

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-loads the capability, then the critical non-verification caveat, then the parameter guidance. Every sentence carries a distinct, actionable fact with no 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 fully describes the return shape (header, claims, time-claim status, risk notes) and the handling caveat. Nothing needed to call this correctly is missing.

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 the two schema descriptions already state the token-in-context tradeoff verbatim, so the description mostly restates structured data. It reinforces the token_env preference but adds no new syntax, format, or constraint beyond the schema.

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+resource ('Decodes a JWT locally') and enumerates the precise output: header, masked claims, time-claim status, and risk notes. An agent can distinguish it from scan_secrets or verify_webhook 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?

Explicitly frames the decoding-vs-verification boundary and steers parameter choice ('Prefer token_env... a token passed as `token` is already in the context'). It stops short of naming a sibling to use instead when actual verification is needed, leaving that inference to the agent.

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

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description adds genuinely new behavior: originals are read only inside the server process and never returned to the model, a notice is prepended to the response, size and file-type limits apply, and redaction is heuristic and may miss custom formats. These are exactly the traits annotations cannot express.

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-loads what the tool does and its safety guarantee before constraints and caveats. Every sentence carries distinct information (output shape, routing, limits, honesty about heuristic gaps); nothing is redundant 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 still describes the return value (redacted content plus findings summary and a leading notice), covers the input contract, failure modes (binary, oversized, non-regular files), and the security-relevant limitation of heuristic redaction. Nothing an agent needs to call it correctly is missing.

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% and the single path parameter is already documented with accepted path forms, so the baseline is 3. The description adds real value by clarifying that a path (not file contents) must be passed and that only regular files within 1 MiB are accepted, tightening how the parameter is supplied.

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 (reads a local text file and returns content with secrets replaced by [REDACTED]) plus the secondary output (findings summary with type, count, line numbers). It also implicitly separates itself from the sibling redact_text by specifying 'Pass a path, not file contents' and from Read/cat by naming them directly.

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?

Explicitly says when to use it ('use this instead of Read or cat for .env files, config files, logs, key files') and enumerates when not to (directories, pipes, devices, binary files, files over 1 MiB). The 'pass a path, not file contents' clause routes the agent away from the text-based sibling.

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

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

Annotations already declare this as a safe, read-only, idempotent operation, but the description adds critical behavioral context: the input text is already in model context and calling the tool does not remove it. It also candidly warns that the heuristic can miss custom formats, which is exactly the kind of limitation an agent needs before trusting the output.

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?

The definition is front-loaded with the core action and return value, then adds the limitation, alternative, and heuristic in a tight sequence. Every sentence earns its place and there is no filler.

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 one-parameter, read-only tool with no output schema, the description supplies everything an agent needs: what it does, what it returns, its key limitation, and the path-based alternative. No essential behavior or routing information is missing.

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%, so the schema already documents the single text parameter. The description and schema both note that the text is already in the model context, but the description does not add format or syntax details beyond what the structured field already provides.

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 states a specific verb and resource: it redacts secrets in text already in context and returns a redacted copy with a findings summary. It clearly distinguishes itself from the sibling redact_file, which is the alternative for avoiding placing secrets into context at all.

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 gives explicit use cases such as redacting before pasting logs into an issue, ticket, chat, or commit message. It also names the alternative and when to prefer it: use redact_file with a path to avoid putting a secret into context in the first place.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds substantive behavior: the output is limited to file:line, type and a masked preview, with exact masking rules (first 4 chars for 20+ char values, ellipsis for short ones). It also warns that a clean result is not proof of safety, which is a meaningful limitation the annotations do not 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?

Four tight sentences, front-loaded with the use case, then parameters, then output shape, then the caveat. Every sentence carries information and nothing is repeated from 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?

With no output schema, the description takes on the job of describing the return shape — which it does precisely (file:line, type, masked preview) — and it flags the false-negative heuristic limitation. An agent has everything it needs to call this correctly.

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%, so the baseline is 3, and the schema already documents recursion, skips and the 2000-file cap. The description adds a small but real clarification beyond the schema: that paths and staged are combinable ('Provide paths, staged, or both'), removing ambiguity about whether the two parameters are mutually exclusive.

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 ('Scans files or directories... for known secret patterns') with an explicit positional context ('Pre-commit check'). It is clearly distinguishable from the redact_* and inspect_jwt siblings, which transform or decode rather than detect.

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?

Gives clear operating context (pre-commit check) and an explicit parameter-combination rule: 'Provide paths, staged, or both.' It does not, however, contrast itself with siblings such as redact_file, which would tell an agent when to scan versus when to redact.

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

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

Annotations already declare read-only, non-open-world, idempotent and non-destructive, and the description adds substantial context on top: secret sourced only from an env var, plaintext secrets rejected, body read as raw bytes, no network traffic, and neither the secret nor a computed signature is returned. This is exactly the kind of behavior an agent cannot infer from structured fields.

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?

Purpose is front-loaded in the first clause, followed by the input contract and then the returned diagnostics. Every sentence carries distinct information with no restatement of the name or 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?

With no output schema, the description takes responsibility for return values and does so explicitly (match/no-match plus well-formedness, Stripe tolerance, body-reformatting and secret-mistake diagnostics). All 6 parameters are documented at 100% coverage and the offline constraint is stated, leaving no material gap.

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%, so the baseline is 3; the description goes further by clarifying the non-obvious secret_env indirection (a variable NAME, never the secret, with rejection of plaintext) and the raw-bytes contract for body_path. It adds the environmental/permission constraint that the schema alone cannot express.

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 ('Verifies a GitHub, Stripe or generic HMAC webhook signature') plus the mode of operation ('locally'). This is clearly distinguishable from siblings like inspect_jwt, file_checksum and scan_secrets 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?

Gives clear context: offline verification of webhook signatures, with an emphasis on diagnosing why a mismatch happened. It does not name alternative tools or explicit when-not conditions, but the usage scenario is unambiguous.

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