CELPass: CELPIP practice and CRS calculator

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real behavioral substance: the award tiers, the 2x/1.5x/1.3x wage thresholds, 'whichever is higher, never both', caps of 150/140, and that no LMIA is needed. It stops short of explaining the return format.

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 purpose is front-loaded, but the body is one sprawling, comma-chained sentence packed with ratios and point values that is hard to parse quickly. The content largely earns its place, yet structure suffers.

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 no-output-schema calculation tool, the description covers inputs, rule precedence, thresholds, and caps thoroughly. The main remaining gap is that the response shape (delta vs. updated total, per-occupation breakdown) is left unstated.

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, and the description goes beyond it by explaining that NOC codes are resolved against IRCC's wage-level list and by tying the caps to spouse_counted. This gives the wage/structure semantics the schema alone does not.

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 (Estimate) and a precisely scoped resource (CRS points gained on Nov 3, 2026 under the new Labour Market Integration factor), with the calculation rules and caps inline. It is unambiguously distinct from the CELPIP and occupation-lookup siblings.

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 caller to supply NOC codes and that only this factor changes, which implies the usage context, but it never names when to pick this tool over find_high_wage_occupation or the CELPIP tools, and gives no exclusions or prerequisites.

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, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds meaningful return behavior: it returns the score, the correct letter for each question, and an explanation of why each option is right or wrong.

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 a single efficient sentence that front-loads the core action and then names the return values. Every clause earns its place, with no repetition or 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 two-parameter, read-only checking tool with 100% schema coverage and no output schema, the description supplies the key missing context: the prerequisite source tool and the return contents. An agent has enough to invoke it correctly.

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 both parameters, including the question-number-to-letter mapping example. The description does not add syntax or format details beyond what the input 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?

The description states a specific verb and resource: 'Mark a learner's answers to a Reading or Listening item from get_celpip_practice_question.' It also names the exact source tool and outputs, letting an agent distinguish it from siblings like get_celpip_practice_question and get_celpip_sample_answers.

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 clear context by tying use to an item returned from get_celpip_practice_question. It does not explicitly state when not to use it or name alternative correction tools, 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?

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavior beyond that: a dated list version, the catalog size, the fact that matches return a wage-level multiple plus earned CRS points, and what a miss implies — all of which an agent needs to interpret empty results.

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, zero filler. The lookup scope and the match output are front-loaded, and the negative case (unlisted = no points) closes it cleanly.

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 one-parameter, annotation-backed, output-schema-less tool, the description does the right thing by summarizing both the accepted inputs and the returned fields (level multiple, CRS points). Fuller detail on match count or result ordering would be nice but is not essential.

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% and the single parameter's schema already gives the same examples ('software engineer', '72201') quoted in the description, so little is added. The description confirms that either free-text job title words or a bare NOC code are acceptable, but that is essentially restatement.

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?

Specific verb (search) plus a named, uniquely-scoped resource (IRCC's high-wage occupation list, 186 NOC 2021 codes) and the two supported query forms. Nothing in the sibling set (CRS calculation, CELPIP tools) overlaps, so an 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?

The description frames the context clearly: the list version in effect (Nov 3, 2026) and the decision-relevant consequence that an unlisted occupation earns no high-wage or job offer points. It lacks an explicit 'use X instead when...' pointer, but no sibling covers this lookup, so the absence is low-risk.

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, destructiveHint=false, openWorldHint=false), and the description adds genuinely useful behavior beyond them: results are random from today's set, the set rotates daily and is identical for everyone, calls are non-idempotent, and Listening provides no transcript. It stops short of describing pagination or rate/limit details, so a 4 rather than 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?

The text is front-loaded with the core purpose and then organized by skill in parallel clauses, so it scans quickly despite its length. It is slightly verbose in enumerating every part range, but nearly every sentence carries actionable information about return content or routing.

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 must convey return content itself, and it does so comprehensively for all four skills, including the important absence of answers and the daily random-set behavior. Nothing an agent needs to call this correctly appears to be 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 coverage is already 100% and the schema itself documents the part ranges and the omission behavior, so the baseline is 3. The description adds value by mapping each part/skill to the concrete content returned (passage+MCQs, listen_url without transcript, prep/speaking times, word counts), giving the agent a richer sense of what a given parameter value yields.

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 opens with a specific verb+resource ('Get one random CELPIP practice item') and then details exactly what is returned for each of the four skill areas, down to listen_url, visual, timing and word limits. An agent can distinguish this from check_celpip_answers and get_celpip_sample_answers purely from the text.

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 states explicitly that no answers are included and names the two alternatives for each case: mark Reading/Listening with check_celpip_answers, compare Speaking/Writing with get_celpip_sample_answers. It also clarifies the 'omit for any part' behavior, leaving little 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, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds useful content-level context: the answer bands returned (4–5, 7–8, 9–10, 11–12) and that responses include an official rating, which goes beyond what the annotations convey.

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: the first front-loads what is returned and its provenance, the second states the use case. No filler or repetition.

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 must convey return content, and it does (sample answers per level band plus CELPIP's rating). Combined with the annotation-covered safety profile and a fully documented single parameter, nothing needed to invoke it 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 coverage is 100% and the single parameter is documented, so the baseline is 3. The description adds real meaning by tying question_id to a Speaking or Writing task obtained from get_celpip_practice_question, clarifying the expected source and valid scope of the value.

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 ('sample answers at several CELPIP levels ... for a Speaking or Writing task') and names the sibling that produces the required question_id (get_celpip_practice_question). An agent can distinguish this from check_celpip_answers and get_celpip_practice_question without opening any 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?

Explicitly states the intended use ('Use them to give the learner feedback on their own answer') and the prerequisite dependency on get_celpip_practice_question. It does not explicitly contrast with check_celpip_answers, 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.