GlaziersEdge Knowledge

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

Annotations already cover the read-only/idempotent/non-destructive safety profile, so the description correctly spends its words on behavior: the expert-estimator sourcing, the per-unit basis (SF/LF/each/LS), the optional low-reliability public cross-checks, and the confidence-tag vocabulary returned in responses. That is meaningful context beyond the structured fields, though return shape details are left to the output 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?

Purpose and the bid-use caveat are front-loaded, which is good, but the long comma-separated scope-item list largely duplicates the schema's scope examples and inflates the definition without adding callable information. Trimming that list would sharpen it.

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 sensibly avoids explaining return fields yet still discloses the confidence-tag scheme and the budget-only limitation. It is close to complete; only the distinction from sibling lookup tools is left implicit.

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 limit, scope, and include_public_crosschecks. The description's scope-item enumeration largely restates the schema's example values, adding only the 'low-reliability public cross-checks' nuance, so baseline 3 is 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: 'Return 2026 US installed budget SELL price ranges' for a glazing scope item, which is clearly distinct from the knowledge/cross-reference siblings. It never explicitly names or contrasts those siblings, so it stops short of a 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 gives an explicit when-to-use ('Budget/sanity-check use only') and when-not ('never for bids'), plus the caveat that ranges vary by region, scope and market. No alternative tool is named for cases where a bid-grade number is required, which keeps it below 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 (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add output context — and it does, disclosing the row structure, basis dimensions, Verified/Flagged status, notes, Topic 29 discontinued notices, and the KB confidence tags. Missing pagination/limit behavior but otherwise rich.

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-loads the input scope and outputs efficiently, with no filler sentences. The single dense paragraph is slightly run-on, but every clause carries routing or verification value.

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, yet the description covers the non-obvious return semantics (confidence tags, Topic 29 notices, basis comparison) that an agent needs to interpret results and route correctly. Nothing critical is missing for this read-only lookup.

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 all four parameters are already documented, including the maker list and category filter values. The description restates the covered vendors but adds no format or syntax detail beyond the schema, so 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?

Names a specific verb (cross-reference/find equivalent) and resource (aluminum framing series) with concrete input examples ('Kawneer Trifab 451', '1600 Wall System 1') and enumerates the vendors covered. It is clearly distinguishable from sibling cross_reference_glass.

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?

States the trigger condition (given a storefront/curtain wall/entrance/window/Interior/Specialty series, return equivalents) and adds a caution that 'equivalent does not mean identical' with the attributes to verify. It does not, however, explicitly name alternative tools or when-not-to-use 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real value beyond that: the three data sources used, the rating taxonomy (Close / Approximate / Not supported by the numbers), and the confidence-tag legend returned in responses. Return-format detail overlaps with the output schema, keeping this 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?

The purpose and input examples are front-loaded in the first sentence, and the enumeration of data sources follows logically. It is dense and citation-heavy (Topic 32 §32.9, Topic 29), but each sentence carries substantive information rather than 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 five-parameter, read-only cross-reference tool with an output schema already defined, the description supplies everything an agent needs: what it does, when to use it, the inputs it accepts, the sources consulted, and the meaning of the confidence tags it returns.

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 all five parameters (product, substrate, target_maker, limit, include_discontinued) are already documented in the schema. The description echoes product examples but adds no syntax, default, or behavioral detail beyond what the schema provides; 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?

The description opens with a specific verb+resource ('Given a glass coating/product ... return equivalents from other makers with a match rating'), immediately distinguishing it from siblings like lookup_glass_performance or search_glazing_knowledge. It also enumerates concrete input examples, leaving no ambiguity about what the tool returns.

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 the use case explicitly ('Use for "or-equal" and substitution screening') and gives a sample query ('SNX 62/27 Vitro equivalent'). It stops short of naming sibling tools or stating when NOT to use it, so it is clear context without explicit exclusions.

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 safety is covered; the description goes further by disclosing paging behavior ('long topics are paged: follow the continue_from hint') and the meaning of the returned confidence tags. It does not mention auth, rate limits, or failure modes, but for a closed-world read tool this is solid added 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 dense sentences, with purpose and the primary routing hint front-loaded before the format examples and tag legend. The tag enumeration is a little long but each entry carries distinct meaning, so little waste.

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-value shape need not be spelled out, and the description still covers paging, tag semantics, and accepted parameter formats. An agent has everything needed to call this correctly on the first try.

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 would be 3, but the description adds accepted input formats beyond the schema ('Topic 30', 'butt glazed', 'sources', 'key', 'bid-day checklist'), which genuinely reduces invocation ambiguity. It adds no extra detail for max_chars, tables_as_records, or continue_from 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?

Opens with a specific verb+resource ('Read the full text of a knowledge-base topic, or a single section of it') and states the scope distinction (whole topic vs single section) up front. It is clearly separable from list_topics and search_glazing_knowledge, which are named as the discovery counterparts.

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 says to use it 'after list_topics or search_glazing_knowledge when you need the complete context (e.g. a whole code table)', naming both alternatives and the condition that selects this tool over them. That is a genuine when-to-use rule rather than implied usage.

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 useful behavior: the response shape (topic numbers, titles, one-line summaries, UNVERIFIED counts) and the confidence-tag vocabulary ([V], [V-mfr], [UNVERIFIED], [inference], [Expert]), which lets the agent interpret results correctly. No auth, rate-limit, or ordering caveats are mentioned, keeping it just under 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?

The core instruction is front-loaded and the confidence-tag legend is a compact, high-value final sentence. The long parenthetical enumerating eighteen topic categories is the only excess; it is informative for scope disambiguation but heavier than necessary.

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, yet it still summarizes them and decodes the confidence tags. It omits the include_sections parameter and any note on response size or pagination, but for a zero-required-parameter listing tool this is close to complete.

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?

There is one optional parameter and schema coverage is 100%, with the schema itself documenting include_sections and its effect ('Also list every section id (e.g. 30.4) per topic'). The description adds nothing about the parameter. Per the high-coverage baseline, 3 is the correct score.

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 ('List the 32 topics in the commercial glass & glazing knowledge base') and enumerates the topical scope in enough breadth that an agent immediately knows what domain this covers. The cardinality (32) and the enumerated categories distinguish it from search_glazing_knowledge and get_topic 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?

Gives a clear selection rule: 'Call this first if you are unsure which topic covers a question.' That is explicit when-to-use guidance. It stops short of naming the alternatives (search_glazing_knowledge, get_topic) or when NOT to use it, so it is strong but not fully routing.

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 the safe read-only/idempotent profile, yet the description still adds genuinely new behavioral context: old names like 'Solarban 70XL' are normalized to current names, values are COG rather than NFRC whole-product ratings, discontinued makeups are included by default, and responses carry confidence tags. These provenance caveats materially affect how an agent should interpret and trust 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?

The opening sentence is well front-loaded, but the middle is padded with exhaustive enumerations — twenty substrate tints and roughly twenty product names / '145 makeups' — much of which duplicates the schema's own product and substrate examples. Trimming those lists would make the definition faster to parse without losing actionable 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?

For an 11-parameter, zero-required filter tool, the description covers the data domain, the filterable dimensions, an example constraint, name normalization, and the COG-vs-NFRC caveat; with a 100% covered schema and an output schema handling return fields, nothing essential to calling 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%, so the schema already documents every parameter and the baseline is 3. The description goes beyond it by giving a concrete filtering example (max_shgc 0.25 for IECC CZ 2) and clarifying that maker/product/substrate accept families and aliases, which helps the agent populate filters correctly.

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 (filter) and resource (manufacturer center-of-glass performance data for 1 in. IGUs) and scopes it tightly to a curated dataset no sibling covers. An agent can immediately tell this apart from search_glazing_knowledge or cross_reference_glass based on the tabular performance-data scope 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?

Usage is only implied through filter examples ('max_shgc 0.25 to meet IECC CZ 2'), not stated as when-to-use versus the sibling tools. There is no explicit routing guidance such as 'use search_glazing_knowledge for narrative answers' or a stated precondition for calling this tool.

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 (readOnly, idempotent, non-destructive, closed-world), but the description adds genuinely useful behavior: BM25 relevance ranking, the 32-topic search scope, and the confidence-tag legend ([V], [V-mfr], [UNVERIFIED], [inference], [Expert]) that an agent needs to interpret results correctly. It stops short of stating pagination/limit behavior or ranking tie-breaks, so it is not exhaustive.

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 the core capability and ranking method, then usage classes, then alternatives, then tag legend — a sensible information hierarchy with no filler sentences. The verbose example list and inline sibling routing make it dense; it is longer than strictly necessary but every clause carries signal.

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 values need not be enumerated, yet the description still characterizes the return shape (cited snippets with topic + section id, tables, tags). Combined with full schema coverage, explicit sibling routing, and tag semantics, an agent has everything needed to call and interpret this tool 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 baseline is 3. The description adds meaning on top: it advises 'use specific technical keywords' for the query and explains what the verification-tag values signify, which illuminates the only_tag enum beyond the bare enum strings. It does not explain topic-number scoping or limit interaction, so it is only slightly above baseline.

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 (keyword search across the glazing knowledge base), names the ranking mechanism (BM25), the corpus size (all 32 topics), and what is returned (cited snippets, tables, verification tags). It explicitly differentiates itself from four sibling tools by naming each one and the data class it owns.

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 both when-to-use ('Best for free-text questions') with concrete example query classes (code requirements, sizing rules, definitions, estimating red flags, lead-time drivers) and when-not-to-use, routing numeric data to lookup_glass_performance, equivalents to cross_reference_glass / cross_reference_aluminum_system, and budget questions to budget_price_range. Nothing is left to inference.

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