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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuinely new context: it discloses the return shape ('returns the top collisions') and a concrete cost characteristic for maxPairs (2,000 pairs under $0.05). It does not discuss defaults or failure modes, so not 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?

Three tight, front-loaded sentences: purpose first, then input forms, then return/cost. Every sentence contributes, with only mild redundancy in 'develop each into a concrete idea'.

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 zero required parameters, the description shoulders return-value explanation reasonably ('returns the top collisions') and covers cost via maxPairs. It remains silent on the 'top' default and what 'lens' does to output, so a small completeness gap remains.

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 60%, so the schema already documents path/notes/items well. The description adds real meaning for maxPairs by tying it to cost, and clarifies path vs notes as alternatives, but it omits any mention of 'top' or 'lens', leaving those parameters to the schema alone.

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 ('find ... combinations in a pile of notes') plus the mechanism ('scoring every pair with Jev'), which is distinctive enough to separate it from generic search tools. It does not explicitly name or contrast any sibling (jev_ask, semantic_bisect, etc.), so 4 rather than 5.

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 tells the agent the accepted inputs ('either a folder/file path or a list of notes') and a follow-up step ('develop each into a concrete idea'), which implies intended usage. However, there is no explicit when-to-use vs when-not, and no routing to alternative sibling tools for related tasks.

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 and openWorldHint=true, covering the safety profile. The description adds the phrase 'low-level access' but does not disclose side effects, rate limits, or result format beyond what annotations provide.

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 description is compact and front-loads the core action before listing question types. It is dense but every sentence earns its place, with only minor jargon in 'Low-level access.'

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?

Given nested object parameters and no output schema, the description thoroughly documents input shapes but says nothing about what the tool returns or how evaluation results are formatted. That omission leaves an agent uncertain about the response format.

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?

Although schema description coverage is 100%, the input schema only describes the questions parameter as a generic object map with additionalProperties: {}. The description compensates by defining three explicit question type structures (noul, choice, score) with their fields and value types, adding substantial meaning not present in 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?

The description states a specific verb and resource: 'evaluate a state against your own typed questions.' It distinguishes the tool as a low-level evaluation primitive, but does not differentiate it from siblings, which appear unrelated.

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 guidance is provided on when to use this tool versus alternatives. There are no exclusions or prerequisites mentioned, leaving usage entirely 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?

Goes well past the annotations (readOnlyHint/openWorldHint) by disclosing the transcription-to-timed-lines pipeline, that pace and pauses affect scoring, the exact reaction taxonomy, and the external dependency that audioPath 'needs a Vercel AI Gateway key'. That is real operational context an agent would otherwise have to discover by failing.

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-loaded with purpose and return shape, then the audioPath branch, then the rewrite guidance. Dense and mostly waste-free, though the reaction list and dual-scoring explanation make it longer than a single-breath definition.

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 carries the full burden of explaining returns, and it does: per-line reaction, joke-vs-sincere classification, laugh/warmth scores, and the 0-100 landed score with its ranking. An agent has everything needed to call it and interpret the result.

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 carries most parameter meaning. The description still adds value by explaining what audioPath actually triggers (transcription, line splitting, pace/pause weighting) and by restating the 200-person default crowd, which clarifies intent rather than just syntax.

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 concrete verb and resource ('Test a stand-up set, speech or pitch on a virtual audience of 200 people') and immediately names what comes back. Nothing in the sibling list (physics_*, steer_check, semantic_bisect, jev_ask) overlaps, so the agent can route to it unambiguously.

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 for the two input paths: pass script for text, pass audioPath to judge a recording, and it tells the agent to use weakest/strongest to drive rewrites. It never states when not to use the tool or names an 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.

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds real value beyond them by disclosing the return shape: outcome, an intensity 0-10 score, and effects with probabilities. It does not mention auth, limits, or determinism, but for a read-only generative tool the disclosed output structure is the main behavioral gap closed.

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 tight sentences, front-loaded with the core action before the return description and the usage instruction. The illustrative parenthetical is short and earns its place; nothing is redundant.

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 returns and does so (outcome, intensity, probabilistic effects). Optional 'how'/'setting' parameters are schema-documented, so nothing essential is missing; auth/limits remain unaddressed but are minor for a read-only 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 coverage is 100% with each of the four parameters described, so the baseline of 3 applies. The description's examples ('a rubber duck and a laser') illustrate the flavor of the a/b pairings but add no syntax or formatting guidance 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?

The description names a specific verb ('resolve') and a clear resource (the outcome of two things meeting) with concrete examples that make the intent unambiguous. It distinguishes itself from rule-based siblings via 'using common sense instead of hand-written rules,' though it never names collision_engine or physics_sandbox 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?

Usage is only implied: the 'common sense instead of hand-written rules' phrase hints this is for ad-hoc, fantastical pairings rather than rule-based collision, and 'narrate the result vividly' tells the agent what to do with the output. No explicit when-to-use/when-not or named alternatives are given, and no sibling (e.g., physics_sandbox, collision_engine) is distinguished.

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 declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds real behavioral detail beyond that: pairwise parallel interaction and results sorted by intensity. It still doesn't explain what an 'event' or 'intensity' looks like in the response.

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 tight sentences with the mechanism front-loaded before the usage hint. Slightly poetic phrasing ('chain of chaos') costs a little precision but nothing is wasted.

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 should clarify return semantics, and 'events come back sorted by intensity' is the only hint. For a 2-parameter simulation tool, the input semantics and output shape are both under-specified.

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 0%, so the description must carry the burden. It does explain the '2-8 things' bound (matching minItems/maxItems) and the single 'setting' string, but never clarifies what kinds of values 'things' should be or how 'setting' is used, leaving the core input ambiguous.

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 conveys a simulation: drop 2-8 objects into a shared setting where all pairs interact. It is evocative but doesn't specify what a 'thing' is or how this differs from siblings like physics_interact or collision_engine, so an agent can't cleanly discriminate between them.

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 narrate a chain of chaos' implies a creative-narration context but names no alternatives and gives no when-not conditions. With physics_interact and collision_engine as siblings, routing guidance is absent.

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: it discloses that execution happens in a temporary git worktree and that 'the user's checkout is untouched,' which explains why destructiveHint=false holds despite running an arbitrary shell command. It also warns that the user's own shell command is executed and must be confirmed, covering the openWorldHint risk profile with concrete 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?

Three sentences, front-loaded with the outcome and followed by mechanism and the safety caveat. Every sentence earns its place 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?

For a six-parameter tool with no output schema, the description conveys the essential model: what it searches for, how it evaluates each commit, and the sandboxing. It omits practical detail an agent might want, such as what the result reports and that the run may be long because the command executes per commit.

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 repo, good, bad, command, symptom, and timeoutSec, making 3 the baseline. The description reinforces the semantics of good/bad/command/symptom in prose but adds no syntax, format, or default detail beyond what the schema 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?

States a precise verb and outcome: 'Find the commit that introduced a problem a normal test can't detect,' which immediately distinguishes it from ordinary git bisect. It goes on to name the mechanism (git worktree, the `command`, the `good`/`bad` range) so an agent knows exactly what the tool produces. No sibling in the provided list overlaps, so no differentiation is needed.

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 qualifier 'a normal test can't detect' tells the agent when this tool is warranted versus a deterministic bisect, and the closing sentence gives an actionable prerequisite (confirm the shell command with the user first). It stops short of stating an explicit when-not or naming an alternative tool, so it is clear context rather than full routing 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description is consistent with them: 'likely invented facts (or unsupported by the given sources)' explains why an open-world check is being performed. However, it never says what a run returns (per-sentence spans? probabilities? reasons?) and never explains how the threshold parameter changes the outcome, which matters since there is no output schema. The phrase 'Rewrite only the flagged sentences' is ambiguous about whether the tool rewrites or the caller does, but reads as workflow advice to the caller rather than a mutation claim.

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 short sentences, front-loaded with the core action and followed by the flagged categories and the retry loop. Tight overall, though the parenthetical in sentence two slightly interrupts the flow and could be folded into the category list.

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 4-parameter tool with no output schema, the description should convey what the agent receives back and how the flag cut-off affects results; it does neither, leaving the agent to infer the return shape. Purpose and iterative use are covered, so it is adequate but incomplete.

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 goal, text, sources, and threshold (including its 0.5-0.95 range and 0.6 default). The description only alludes to 'sources' parenthetically and never mentions the threshold, so it adds no meaning beyond the structured fields; 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?

A specific verb+resource: 'Judge every sentence of a draft against its goal,' followed by the exact failure classes it flags (off-goal, filler, repetitive, invented/unsupported facts). No sibling in the provided list overlaps with this function, so no differentiation is needed and none is missing.

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 operating loop: check the draft, rewrite only flagged sentences, then re-invoke to confirm. That tells the agent when and how to use it, but there is no explicit exclusion or named alternative for cases where sentence-level judging is the wrong tool (e.g. whole-document structure).

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