Jagent

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

Annotations only cover the safety profile (readOnlyHint, openWorldHint), so the description carries the rest and does so well: it discloses the 0-100 match score, keyword matching semantics ('matched literally, as an ATS search would'), ATS format checks, level fit, and recruiter interview probability. It stops short of noting rate limits, input size limits, or determinism, so it is 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?

A single front-loaded sentence opens with the verb and resource, then lists the return payload in a compact colon-delimited series. Every clause earns its place with no filler or repetition of the name.

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 return-value burden and does so by enumerating every score component the caller receives. Combined with the 100%-covered input schema, an agent has everything needed to invoke and interpret the 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 in the schema and the baseline is 3. The description reinforces that job_description is optional and that matching is literal/ATS-style, which is useful but adds little beyond what the schema already states.

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 uses a specific verb+resource ('Score a resume') and enumerates the exact outputs produced, which cleanly separates it from the essay/rubric/choice grading siblings whose names imply non-resume artifacts. It does not explicitly name or contrast against any sibling, so it lands at a clear-but-undifferentiated 4.

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?

'optionally against a job posting' implies the two modes of usage but never states when to prefer this tool over grade_with_rubric or the other scoring siblings. The conditional is inferable rather than explicit, and no exclusions or prerequisites are given.

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?

Beyond the readOnlyHint/openWorldHint annotations, the description discloses internals an agent could not otherwise know: the comparison is run twice with order swapped and averaged, this exists to counter a second-option bias, and disagreement resolves to a tie. That materially changes how results should be interpreted and reported.

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 core purpose and then the tie-breaking behavior; no filler. The first sentence is a subject-less fragment, which slightly blunts immediate readability.

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 read-only judging tool with no output schema, the description covers the most important unknown: that the outcome may be a tie. It does not describe the response shape or how the averaged verdict is represented, though it does confirm the ordering behavior an agent must account for.

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 only 50% (context and question are described in the schema; version_a and version_b are not), and the description does not compensate for the gap, referring only obliquely to "a stated purpose." Parameter names are largely self-explanatory, which keeps this from being a 1, but the description adds essentially no parameter meaning.

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 opening sentence states a specific comparison task ("Which of two versions is stronger for a stated purpose") with a clear input pair and evaluation dimension, so an agent can tell it apart from pass/fail tools like judge_yes_no. It does not, however, contrast itself with the closest sibling, judge_choice, which may also be a pairwise comparison, leaving some ambiguity.

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 implied by "for a stated purpose" and the two-version input shape, but there is no explicit statement of when to pick this over judge_choice or grade_with_rubric. No exclusions or prerequisites are given.

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=true) and openWorldHint=true, so the bar is lower. The description adds meaningful behavior beyond that: the per-kind output shape ('six criteria and a letter grade', 'Reading/Analysis/Writing each 1-4') and the caveat that the SAT source passage is used to check quotations, which is not derivable from the schema.

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 paragraph that front-loads the core action before branching into per-kind detail. Sentences are compact and clause-packed, with no filler, though the kind-by-kind enumeration makes it slightly dense 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?

No output schema exists, so the description usefully supplies expected outputs per kind. It covers all three modes and the required parameters, leaving only minor gaps (no mention of latency, failure modes, or the 20,000-character input limit).

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?

With 83% schema coverage the baseline is 3, but the description adds real meaning: it explains what each 'kind' enum value does, clarifies that 'level' is essay-only, and ties 'prompt' to the seven Common App prompts with the default of 7. These kind-parameter interactions go beyond the schema's field-level descriptions.

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 ('Grade one essay against a built-in rubric') and enumerates the three modes (essay, common-app, sat) with what each produces. The phrase 'built-in rubric' implicitly separates it from the sibling grade_with_rubric, but the sibling is never named, so differentiation is left to inference.

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 description gives conditional usage for parameters by kind ('pass the prompt number, 1-7', 'pass the source passage to check quotations'), which implies when each mode applies. However, it never states when to choose this tool over grade_with_rubric or the judge_* siblings, and there are no exclusions, so the alternative-selection guidance is missing.

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 only cover readOnlyHint/openWorldHint, but the description adds real behavioral context: submissions are graded in parallel and each is scored in its own call so scores are independent of the others — an important determinism guarantee an agent would not otherwise know. It does not contradict the read-only annotation.

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 filler; the batch/parallel scope and the rubric mechanism are front-loaded. Every clause carries 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 should explain the return shape (per-criterion scores and per-submission sums). 'Summed per submission' hints at the result but is thin, and the `assignment` parameter is undocumented anywhere — an agent lacks enough to invoke it fully.

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 only 25%, so the description does some compensating work: it explains the rubric criteria concept, the 3-6 point scale (the `points` parameter), and the 30-submission cap. However it never mentions the `assignment` parameter or that criteria are capped at 8, leaving meaningful gaps at this coverage level.

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 (grade), resource (submissions) and mechanism (rubric you supply) with scope limits (up to 30, parallel). 'A rubric you supply' implicitly distinguishes it from the built-in grade_essay, but no sibling is named, so the differentiation is left to inference.

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 description conveys the usage context (custom rubric, batch of up to 30, 3-6 point scale) but never says when to prefer grade_essay, judge_score, or judge_choice instead, nor any prerequisites. Usage is implied rather than routed.

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, so the safety profile is covered. The description adds useful output behavior (a probability for every option plus a confidence), but says nothing about input limits, handling of malformed options, or the overall-loop/model used.

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 no filler. It could be marginally tighter, but every clause carries information about behavior or the options parameter.

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 usefully discloses the return shape (per-option probability plus confidence), and annotations cover read-only safety. Minor gaps remain around input constraints (e.g. 60k text limit) and error behavior, but nothing essential for calling the tool 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 only 33% – only 'options' is documented in the schema – but the description does clarify the least obvious parameter ('Options map an id to a description of when it applies'). 'text' and 'question' remain undocumented in both places, though their names are largely self-evident.

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 ('Pick the option that best fits a text') and names the return shape (probability per option plus a confidence). It clearly conveys multi-class classification, but never differentiates itself from siblings like judge_yes_no or judge_score, so the agent must infer the boundary from the name alone.

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?

There is no when-to-use guidance and no mention of alternatives, even though judge_yes_no and judge_score clearly overlap in the sibling set. The agent must infer that 'multiple-choice with >2 options' is the selector condition without being told.

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 cover the safety profile (readOnlyHint, openWorldHint), and the description adds real behavioral value by disclosing the return shape: nearest level, exact position, and a per-level probability. No output schema exists, so this return disclosure is the only source for it.

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 that states the action, the ordering convention, and the three returned values with zero filler.

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 read-only, three-parameter tool with no output schema, the description adequately covers the return values but omits the role of 'question' and any limits (2–10 levels, 60k character text). An agent can invoke it, but not confidently understand how the question steers the scoring.

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 only 33%, so the description must compensate. It reinforces the levels semantics ('lowest level first'), which duplicates the schema description, but leaves 'question' — the scoring criterion driving the judgment — entirely unexplained in both schema and 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 and resource ('place a text on an ordered scale you define') plus the outputs produced, which distinguishes it from binary/choice siblings like judge_yes_no and judge_choice. It stops short of naming those siblings explicitly, so the differentiation is inferable 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?

There is no when-to-use guidance and no routing against the six sibling judge/grade tools. 'A scale you define' implies a custom ordinal use case, but the agent gets no signal about when to pick judge_score over judge_choice or grade_with_rubric.

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 since there is no output schema, the description usefully discloses the return type: a probability that the answer is yes. It does not mention limits like the 60000-char text cap, but that is documented in the schema.

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: capability and return type front-loaded, followed by a concrete usage example. No filler.

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?

No output schema, so the description's disclosure of the probability return is valuable, but with 4 parameters at 50% schema coverage the roles of no_means/yes_means go unexplained. Adequate but with a clear gap for the optional steering parameters.

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 only 50% (question and no_means have no schema descriptions). The description adds no meaning for those parameters and only implicitly signals that text+question are the inputs via its example. It does not explain how no_means/yes_means steer the judgment.

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 (ask a yes/no question about text) and the return value (probability of yes). The 'yes/no' framing implicitly distinguishes it from siblings like judge_choice and judge_score, though no sibling is named 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 clear usage context ('checks and gates') plus a concrete example question, which tells an agent when this tool fits. It lacks explicit exclusions or named alternatives (e.g. when to prefer judge_choice over judge_yes_no).

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