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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: diffs are token-optimized and automatically truncated to max_diff_lines (default 400). It stops short of saying whether truncation is signaled in the output, which is the one open behavioral question.

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 sentences, no redundancy, and the core capability is front-loaded ahead of the usage hint and the truncation caveat. Every sentence carries distinct information.

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 (metadata, author, message, diffs). Annotations cover safety. The remaining gap is behavior under truncation for very large commits, but nothing essential for correct invocation 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 baseline is 3; the description earns an extra point by explaining the intent behind max_diff_lines (context-token conservation) and reinforcing that ref accepts SHA, branch, or tag. It doesn't describe the optional file_path filter, but the schema covers that fully.

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 ('Get detailed commit metadata... and unified git diffs') scoped by 'a specific commit SHA or reference'. This clearly separates it from siblings like get_file_contents and get_repository, which target files and repositories rather than a commit ref.

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 usage context ('reviewing code modifications, patches, or investigating regressions'), which tells the agent when this tool is appropriate. However, it names no alternatives or when-not conditions, so routing versus siblings such as get_file_contents is left to inference.

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 the safe read-only, idempotent, non-destructive profile, so the bar is lower. The description still adds real value by disclosing that no clone is required and that Base64 payloads are auto-decoded into a 'decoded_content' field, which materially affects how the agent consumes the result.

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 dense sentences that are front-loaded with the core capability before the decoding detail and usage framing. 'Eager daily driver tool' is mildly promotional filler, but everything else earns its place.

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 partially compensates by naming the 'decoded_content' return field and the directory-listing mode. Combined with the annotations and full schema coverage, an agent has enough to call it correctly, though pagination and error behavior are unmentioned.

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 all four parameters (owner, repo, path, ref) are already documented with examples and defaults. The description reinforces the dual file/directory semantics of 'path' and the ref concept but adds no syntax or format detail beyond the schema, so the 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 specific verb (read/list) and resource (repository file or directory) at a git ref, and covers both operating modes explicitly. An agent can immediately distinguish it from get_repository (metadata) and get_commit (history) 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 concrete usage context ('inspecting source code, configuration files, and directory layouts') and labels itself a frequent 'daily driver' tool, which tells the agent this is the default choice for reading repo content. It stops short of naming when NOT to use it or pointing at a sibling alternative.

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 readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds the useful behavioral note that this is intended as a frequent, cheap verification call, but says nothing about authentication requirements, rate limits, or failure behavior for nonexistent repos.

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 compact sentences with the returned payload front-loaded before the usage note. The phrase "Eager daily driver tool" is mildly promotional filler, but the rest is dense and earns its space.

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 burden of describing return values and does so by enumerating the metadata fields. For a two-parameter, fully-annotated read tool this is essentially complete; only the error behavior for a missing repo is unaddressed.

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% — both owner and repo are documented with concrete examples in the schema itself. The description only restates "for an owner/repo" and adds no format, casing, or validation detail beyond what the schema provides, so the baseline of 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?

The description gives a specific verb (get) and resource (repository) and enumerates the returned fields — metadata, visibility, description, default branch, clone URLs, star count, topics — so the agent knows exactly what comes back. It does not explicitly contrast itself with siblings like get_file_contents or get_commit, but the resource is distinct enough that confusion is unlikely.

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?

"Eager daily driver tool for verifying repository configuration and existence" implies the usage context (existence/configuration checks) but names no alternatives and states no when-not conditions. Usage is implied rather than prescribed, which is the definition of a 3.

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 well beyond the annotations by disclosing that output is lossily compressed via strict token projection filters (URLs, avatar links, empty hashes, node_ids stripped) with a claimed 70%+ token saving, and that mutation is environment-gated. That output-truncation disclosure is exactly the kind of behavior an agent cannot infer from readOnlyHint/destructiveHint alone.

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 dense sentences that are front-loaded with the execution contract before moving to prerequisites and output behavior; little waste. The '70%+ token savings' claim borders on promotional but still conveys expected output shrinkage.

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 adequately via the format enum and compression note, and it covers the dynamic-parameter discovery path. It leaves error behavior for blocked mutating actions and partial-schema mismatches unstated, which is a minor 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, but the description adds real meaning for the polymorphic 'params' object by framing it as the argument dictionary matching the selected action's own schema and pointing to github_find_actions as the way to learn that schema. The static schema cannot express that per-action contract, so the description earns above 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?

States a specific verb (execute) and resource (a named action from the 75-action catalog) with the dispatch mechanism spelled out: action name plus argument dictionary. It is clearly separable from github_find_actions, which is named as the discovery step rather than the executor.

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 an explicit prerequisite (the exact action name must come from github_find_actions) and an explicit environmental exclusion (mutating actions blocked under GITHUB_READ_ONLY=true). It does not clarify when to prefer this generic dispatcher over typed siblings like get_file_contents or get_repository, which overlap with catalog actions.

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 readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds real value beyond that: catalog size (75 actions), the existence of 3 eager daily drivers, and the fact that results include mutating flags plus complete parameter schemas for building the follow-up call.

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, zero waste, front-loaded with the core purpose and then the usage rule. The dense second sentence is entirely load-bearing (scope, trigger condition, examples, return shape).

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, but the description enumerates what is returned (action names, domain categories, mutating flags, descriptions, full parameter schemas), so an agent knows exactly what it gets back. Combined with the annotations, 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%, so the schema already documents query, domain, and format in detail. The description restates the two filtering modes but adds no syntax, matching behavior, or edge-case guidance beyond what the enum and parameter descriptions provide; 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 specific verb+resource ('Search and discover available GitHub actions in the 75-action catalog') with the two selection axes (keyword query or domain filter). It clearly distinguishes itself from the sibling github_execute_action by being the discovery step that feeds it.

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 'Use this discovery tool first whenever you need to perform an action outside the 3 eager daily drivers' and lists the domains that qualify (PRs, issues, releases, workflows, collaborators, webhooks, variables, security alerts). It also names the downstream tool to construct the call for, github_execute_action.

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