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

No annotations, so the description carries the full burden. It usefully defines the 'flaky' criterion, the sort order, and that counts are included, but says nothing about result limits, truncation, lookback default behavior at the 90-day cap, or permissions.

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?

A single front-loaded sentence with the resource first and the definition, ordering, and output shape packed in without waste. Every clause 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?

For a simple one-parameter read tool with no output schema, the description covers what is returned (counts, ordering) and the semantics of flakiness. Only edge details like result caps or the interpretation of the maximum window are absent.

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 0%, but there is only one self-explanatory integer parameter ('days'). The phrase 'last N days' confirms it is a lookback window, matching the schema default of 14, but the description adds no detail beyond what the parameter name already conveys.

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 resource (flaky tests) with an explicit definition of 'flaky' (failed then passed on retry), plus ordering and payload (most flaky first, with counts). This is clearly distinguishable from a generic test-history or recent-runs tool, though no sibling is named 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?

No when-to-use guidance and no alternatives named. It is implied that this is for investigating flakiness rather than viewing runs, but an agent gets no explicit trigger or exclusion relative to turnsignal_test_history or turnsignal_recent_runs.

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 burden: it discloses sort order ('newest first'), the exact fields returned (verdict, status, branch, commit, counts, run id), and the scope restriction to 'this project'. That is substantive behavioral context for a list tool, though pagination/limit behavior is left unstated.

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, no filler: the first front-loads what comes back and in what order, the second states the usage. Every clause 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?

Since there is no output schema, the description usefully enumerates return fields, and the absence of annotations is partly offset by the ordering and scope notes. However, it omits the filtering semantics of 'branch' and the cap behavior of 'limit', leaving an agent to guess at invocation details.

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?

The schema only documents 'branch' (50% coverage), and the description says nothing about either parameter – it never mentions that 'branch' filters results or that 'limit' caps the count. Listing 'branch' among returned fields could even mislead an agent into thinking it isn't also a filter.

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 ('Recent CI runs of this project') and even enumerates the fields returned plus the sort order, which is more than most list tools do. It doesn't name a sibling, but 'find a run to inspect' implicitly distinguishes it from turnsignal_run.

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?

'Use it to find a run to inspect' gives a clear selection context and quietly points at turnsignal_run as the follow-up tool. No explicit when-not or exclusions are given, so it stops short of a 5.

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?

No annotations are provided, so the description carries the full burden. It discloses the return contract in detail (failure classification, new-vs-default-branch status, artifact links), which is the main behavioral disclosure an agent needs for a retrieval tool with no side effects. It says nothing about auth requirements, rate limits, or what happens if both runId and runKey are supplied, which keeps it from 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?

A single dense sentence whose first clause states the purpose and whose remaining clauses enumerate the payload, followed by a short sentence covering invocation. Every clause carries information and the scoping/precedence rule is front-loaded after the purpose.

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 must explain both the return payload and how to target a run, and it does both. The only gap is the branch parameter's interaction with runId/runKey and the absence of any operational notes (auth, limits), which is minor for a read-only retrieval 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 low (33%: only 'branch' is documented), so the description must compensate and largely does, explaining the meaning and precedence of runId, runKey (with format example), and the 'neither' fallback to the latest run. It leaves the interplay with the branch parameter (branch only vs. branch with id/key) unstated, so it is not fully complete.

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?

Opens with a specific verb+resource framing ('One run explained') and enumerates exactly what the run detail contains (verdict, failed/flaky/missing tests with file:line, error, snippet, new-vs-default-branch, trace/video/screenshot). This is clearly distinguishable from the sibling list/history/flaky tools, so an agent can route 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?

Gives explicit selection guidance: pass runId, or runKey (with a concrete example format 'github:1234567'), or neither for the latest run. It does not name the siblings (e.g., turnsignal_recent_runs as the way to obtain a runId) or state exclusions, so it stops short of full when/when-not guidance.

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?

No annotations are provided, so the description carries the full burden. It discloses the ordering (newest first) and the returned fields, which is useful behavioral context, but says nothing about limits, pagination, or what happens when no runs exist for the test.

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 tightly written sentences with no filler; purpose, output shape, use case, and parameter provenance are all front-loaded.

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 simple two-param read tool this is close to adequate, but with no annotations and no output schema, the description should clarify mutation safety (it's implicitly read-only but never says so) and the limit behavior.

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 0%, but only two parameters exist. The description explains testKey's provenance ('comes from turnsignal_run'), which is valuable, but the 'limit' parameter is left entirely undocumented in both the schema and the description.

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: returns one test's recent results across runs, ordered newest-first, with the returned fields named (outcome, branch, run). This is distinguishable from siblings like turnsignal_flaky_tests and turnsignal_run.

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 clear use case: 'Use it to tell a new breakage from a long-flaky test.' That's a genuine when-to-use signal. It doesn't explicitly contrast with the sibling turnsignal_flaky_tests, which is the closest alternative, so it stops short of a 5.

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