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 read-only/idempotent/non-destructive, so the lower bar applies. The description adds real value beyond them: it discloses the return shape (topic numbers, titles, one-line summaries, UNVERIFIED counts) and documents the confidence-tag vocabulary ([V], [V-mfr], [UNVERIFIED], [inference], [Expert]). That tag legend is behavioral context an agent cannot get from structured fields.

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 verb and primary guidance are front-loaded, and the confidence-tag sentence earns its place. The 18-item parenthetical coverage list is long and partially restates content the tool itself returns as topic titles, so it is slightly 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?

For a zero-required-parameter listing tool with an output schema, the description is complete enough to invoke correctly and to interpret the confidence tags. It redundantly describes return fields the output schema already covers and never mentions the one optional parameter, keeping it from a 5.

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 include_sections is fully documented in the schema, so the description is not obliged to add parameter detail. It mentions section-level output only indirectly ('include_sections' is never referenced), so baseline 3 is correct.

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 (List) plus the resource and its exact size, and enumerates the subject coverage so an agent can tell it apart from search_glazing_knowledge and get_topic without opening a 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?

'Call this first if you are unsure which topic covers a question' gives a clear trigger condition and implicitly routes to get_topic once a topic number is known. It does not explicitly state when not to use it (e.g. when the topic is already known), so it falls 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 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 read-only, idempotent, non-destructive, and closed-world behavior, so the safety profile is settled. The description adds genuinely new context beyond that: the BM25 ranking method, that snippets come with topic + section citations, and the meaning of the confidence tags preserved in responses. It stops short of stating pagination/truncation behavior for the limit cap, which keeps it at a 4 rather than 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?

Front-loaded with purpose and return shape, then usage, then sibling routing, then tag legend — a sensible priority order with no filler sentences. The example list is long but each example maps to a distinct question class, so it earns its space; the block is still dense enough to be slightly heavy for a search tool.

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 is not obligated to enumerate return values, yet it still explains the citation format and confidence-tag semantics an agent needs to interpret results correctly. Retrieval method, scope (34 topics), usage routing, and query strategy are all covered.

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, but the description adds real guidance the schema lacks: how to phrase the query parameter ('Use specific technical keywords') and how to read the only_tag values via the confidence-tag legend. The topics and limit parameters are left to their schema descriptions, so the boost is partial.

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 ('Keyword search ... across all 34 topics') plus the retrieval mechanism (BM25 relevance ranking) and the return shape (matching sections with cited snippets, tables, verification tags). It explicitly distinguishes itself from siblings by naming the tools that handle numeric data, product equivalents, and budgets.

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 best-fit class of question ('Best for free-text questions') with concrete examples spanning code requirements, sizing rules, definitions, estimating, lead times, and testing standards, plus the tactic 'Use specific technical keywords.' It then routes four adjacent use cases to the correct sibling tools, so an agent rarely needs to guess.

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