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

Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-obvious behavior: coverage is derived from the data, which disagrees with upstream metadata for 22 metrics. That caveat is real value beyond the annotations, but error handling and response shape for bad targets are unaddressed.

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 purpose sentence, then the LINK PEOPLE TO THE SOURCE block, then arg documentation — well ordered and mostly tight. Minor padding in "it beats paraphrasing, and it is where the framework lives" and the all-caps emphasis costs a little economy.

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 single-parameter tool with an output schema, this is complete: purpose, the coverage-accuracy caveat that affects trust in the answer, full target syntax, and guidance on relaying the source link. Nothing an agent needs to call 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?

With 0% schema description coverage and no enums, the description carries the full burden and does: it documents the mNN / iN / eqN prefixes, the bare-number default (metric), and the two special targets "framework" and "disaggregates". An agent can construct a valid target without guessing.

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 ("Explain") and a precise resource ("one Education-to-Workforce metric, indicator, or essential question") plus the returned scope (years, geographies, framework link). It implicitly separates itself from get_data by framing the answer as definition/evidence "rather than a number", though no sibling is named outright.

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 condition — pass the framework link along when someone wants the definition, evidence or measurement guidance rather than a number — which implicitly routes numeric requests to get_data. No explicit exclusions or prerequisites (e.g., unknown target behavior), 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?

Beyond the read-only/idempotent annotations, the description discloses substantial behavior: benchmarks added automatically, demographic context for states, uneven coverage by geography, and the critical caveat that there are NO margins of error, sample sizes or denominators so differences must never be called significant. This is exactly the kind of context annotations cannot 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?

The purpose and selection options are front-loaded, and every section (benchmarks, coverage caveats, args) earns its place. It is somewhat long, but the length is justified by the 0% schema coverage and the genuine nuance in the dataset.

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 an output schema present, the description need not explain return values, and it fills the remaining gaps: parameter meanings, auto-added benchmarks, coverage unevenness, and the statistical-misuse warning. Nothing an agent needs to call this 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 0%, so the description carries the full burden and does so thoroughly: it explains each of the 8 parameters, gives comma-separated syntax examples for metric_ids/years/geo_ids, clarifies state as 2-digit FIPS, and specifies that disaggregate accepts a dimension or a single group code.

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 ('Fetch Education-to-Workforce metric values for places, or rank places on a metric') and covers both listing and ranking modes. It also distinguishes itself from sibling resolve_place by explicitly directing geoid sourcing there.

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 clearly lays out three mutually exclusive ways to select places (geo_ids, state, rank) and adds constraints like 'Ranking requires a single group code' and 'Omit for all' on years. It routes to resolve_place for geoids, though it doesn't explicitly state when to prefer this tool over siblings like search.

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 genuinely new behavior — it returns ranked candidates, deliberately does NOT auto-pick, and explains the ambiguity risk (duplicate county names, wrong-grain picks). It stops short of describing candidate payload shape, but the output schema exists for that.

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, then the no-auto-pick behavior, then the routing escape hatch, then args. Every sentence earns its place, though the Washington County illustration is slightly verbose and the mid-paragraph 'ASK' instruction interrupts the flow.

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?

An output schema exists, so return shape needn't be explained, and the description still tells the agent how to use results (name the chosen place and geoid in the answer). For a two-parameter read-only resolver, nothing an agent needs to call 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 description coverage is 0%, so the description carries the load, and it does: it defines 'name' with example formats ('Cook County', 'Chicago Public Schools') and the NCES-naming convention, and enumerates the three legal 'geo_level' values. It adds real meaning beyond the bare schema, though it does not state what happens when geo_level is omitted.

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+outcome: 'Find the state, county, or school-district geoid used by get_data.' It also implicitly distinguishes itself from the get_data sibling by identifying itself as the name-to-geoid resolution step that feeds it.

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?

Explicit routing rules: skip this tool entirely for statewide queries and use get_data(state="12") instead, and ASK the user when candidates span geo levels. Both the when-to-use and when-not-to-use cases are named with concrete conditions.

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/closed-world, so the bar is lower, yet the description adds genuinely non-obvious behavior: per-word matching that ignores word order, definition-level matching so differently-worded metrics still hit, and an explicit coverage boundary (no individual schools, colleges, or local labour market data; stops at district). This beyond-annotation context is exactly what prevents silent misuse.

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 matching behavior, then coverage limits, then the argument semantics. Every sentence either defines capability, prevents a misuse, or documents the parameter; nothing is 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?

With an output schema present, return values need no explanation, and the description covers purpose, matching semantics, coverage boundaries, defaults, and the sole parameter's meaning. An agent has everything needed to select and call this 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 0% and there is a single parameter, so the description must carry it — and it does, defining query as 'a concept' with concrete examples ('gifted', 'student debt', 'chronic absence') and stating that omitting it returns the 20 essential questions. This is far more than the bare 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?

The description states a specific verb and resource — browsing the Education-to-Workforce Framework and finding metrics by concept — and even explains the matching mechanism (metric/indicator names plus framework definitions). It does not explicitly contrast itself with siblings like describe or get_data, but the purpose is unambiguous on its own.

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 gives explicit guidance on how to invoke ('try a short multi-word phrase before assuming something isn't covered'), a recommended default ('omit query to list the 20 essential questions, which is the best starting point'), and a when-not-to-answer rule ('NOT COVERED... say so rather than answering from a different grain'). That is when/when-not/alternatives all in one place.

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