KarmaDue

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

Annotations only declare readOnlyHint, but the description discloses the enforcement ladder, the returned fields (v, enforce, why, fix, do_not, test, source, safety), and the sole write-like side effect ('the only case where this call records anything: one anonymous request'). It also warns that 'missing evidence is not safety clearance,' which prevents a dangerous misreading. Consistent with readOnlyHint=true.

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 trigger ('Read-only. Call before ...') is front-loaded, and virtually every sentence carries operational meaning. It is dense and slightly run-on with inline result-field glosses, but nothing is 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?

There is no output schema, so the description correctly carries the full burden of explaining return values and how to interpret enforce/v/safety. Combined with the skip rule and the request_repro path, an agent has everything needed to call and act on it.

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 schema descriptions already explain target, ecosystem, detail, runtime_env, and request_repro. The description restates install-target formatting and the ambiguous-bare-name behavior but adds little beyond the schema, so 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 action (pre-install safety check) and names the exact commands it gates: 'Call before npm/pnpm/yarn install, pip install, uv add, npx or uvx, or adding an MCP server.' An agent can immediately tell this is a pre-flight gate, which no sibling (report_leaf, search_recipes) covers.

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 explicit trigger conditions (including setup commands from READMEs/tutorials) and an explicit exclusion: 'Skip packages already pinned in a lockfile you are not changing.' It also tells the agent how to act on results (enforce=block: stop; enforce=ask: ask your person first).

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?

With only readOnlyHint=false in the annotations, the description carries most of the behavioral load, and it does add real context: owner opt-in gating and a 'Reviewed before use' moderation step, which signals that submissions are human-screened. 'Reviewed before use' is slightly ambiguous about reviewer and turnaround, and there's no mention of what happens to rejected reports or whether this tool can fail.

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?

One tight sentence with the gating condition front-loaded, followed by a short moderation note; nothing is padded. The trailing fragment 'Reviewed before use' is telegraphic enough to be slightly unclear on first read.

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 mutation-style telemetry tool with no output schema and minimal annotations, the description covers the trigger and the opt-in gate but says nothing about the response, whether the call can fail, or what a rejected report means for the agent. Adequate to invoke, incomplete for understanding the full interaction.

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%, including the pass/fail enum and the 'No secrets or tokens' constraint on command_run, so the schema already supplies rich meaning. The description's 'report pass or fail and the command' merely restates the status and command_run fields without adding format, length, or validation guidance.

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 concrete verb+resource pairing: report the pass/fail outcome and the install command after an install completes. It implicitly contrasts with the pre-install sibling check_install via the 'after an install finishes' timing, but never names that sibling explicitly, so differentiation is inferred 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?

It gives a clear precondition window ('after an install finishes') and an explicit gate for when not to use it ('Only if your owner opted in'). It stops short of naming check_install or search_recipes as alternatives, so the routing is left partly 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 readOnlyHint=true, so the safe-read profile is covered. The description adds that the result is 'tested fixes' and that the input should be verbatim, which is useful, but it says nothing about result ordering, breadth, or whether results can be empty.

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 short sentences, front-loaded with the triggering condition, and the second sentence covers input handling and output in one clause. No wasted words.

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 two-parameter read-only lookup with full schema coverage, the description supplies the trigger, the input expectation, and a rough sense of the return value. With no output schema, a little more on what a result looks like would make it fully complete.

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 both parameters are already documented in the schema. The description reinforces the error_signature semantics ('paste the key error line') but adds no format or syntax detail beyond what the schema provides, 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?

The description makes clear what the tool does: it takes an error line and returns tested fixes for install/build/import failures. It is specific about the trigger and the output, though it never names or differentiates itself from siblings check_install or report_leaf.

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 timing guidance ('Call when an install, build or import fails') and a when-not ('before retrying or guessing a fix'), which is strong context. It stops short of naming an alternative tool to use in adjacent situations.

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