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

No annotations are present, so the description carries the full burden, and it discloses the key non-obvious trait: incremental compilation skips unchanged files and suppresses their warnings, which explains seemingly missing diagnostics. It also implies compile errors are returned as data rather than thrown, but does not state failure semantics, permissions, or whether a run can partially succeed.

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 the action and return shape, then the caching caveat with its remedy. Every clause carries information an agent needs.

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 and no annotations, the description still names the return item fields and the caching behavior, which is enough to call it correctly. It leaves open what a total compile failure looks like in the response, a minor gap for a two-parameter tool.

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; the description only restates force's effect and says nothing about max_bytes, the response-size budget, which is the less obvious of the two knobs.

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 ("Compile the project with `forge build`") plus what it returns (errors and warnings with file/line/column/code/message). It is clearly distinguishable in practice from run_tests and explain_failure, though it never names those siblings explicitly.

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 a concrete condition for the one meaningful option: pass force: true when you need warnings from unchanged files re-reported. It does not say when to prefer this over run_tests or explain_failure, so the alternative-selection guidance is implied rather than stated.

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 no annotations, the description carries the full load and does so well: it discloses that the test is re-executed, that output is filtered to that single test, that the decoded call trace is trimmed to the path to the revert when long, and that fuzz/invariant tests yield a counterexample. It omits cost/side-effect implications of re-running and any permission notes, keeping it short of a 5.

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 dense sentences with no filler; the core action leads and the naming requirement closes. Every clause adds something an agent would otherwise have to guess.

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 burden of explaining return contents and does — reason, trimmed call trace, backtrace, logs, counterexample. It stops short of describing the `max_bytes` budget or `contract` override, though both are documented in the schema.

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 still adds real value by giving a concrete format example ('BankTest.test_transfer()') and tying the naming convention to what run_tests emits. It does not mention `contract` or `max_bytes`, which remain schema-only.

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 ('Re-run one test at high verbosity and return only that test') and immediately scopes it against the sibling run_tests, which runs whole suites. An agent can tell exactly what this produces without opening the 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?

Guidance is implicit but strong: this is the drill-down step after run_tests reports a failure, and the description tells the caller to pass the test name 'as run_tests reports it'. It lacks an explicit 'use run_tests instead when...' exclusion, but the relationship to the sibling is clear enough to route correctly.

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 no annotations, the description carries the burden well: it explains the compact summary contents, failure kinds, decoded reasons, counterexamples, logs, and the critical `isError` semantics. It does not mention side effects such as build artifact writes or permission requirements, but the core behavioral contract is clearly disclosed.

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 dense sentences with zero waste. The primary action and return shape are front-loaded, followed by the essential error-handling caveat.

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 test runner with optional filters and no output schema, the description sufficiently explains what is returned and how errors should be interpreted. It could be slightly more complete by mentioning how it relates to sibling tools or by noting potential build side effects, but the essential context is present.

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 all six optional parameters in detail. The description adds no parameter-specific information beyond what the schema provides, making the baseline 3 appropriate.

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 ('Run `forge test`') and resource/action, plus the exact return shape. It is clear what the tool does, but it does not explicitly distinguish itself from siblings like `explain_failure` or `build`.

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?

Provides an important usage caveat about `isError` not meaning passing tests, but gives no explicit guidance on when to choose this tool versus `explain_failure` or `build`. Usage is implied by the test-running purpose rather than stated as a decision rule.

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