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

Annotations already declare readOnlyHint and openWorldHint=false, so the safety profile is known; the description reinforces it with 'Runs locally; nothing is uploaded,' which is meaningful for a tool whose inputs may be URLs. It also discloses the response contents (per-specification pass/fail, applied/passed/failed counts, first failures with element and reason), which matters because there is no output schema. Not exhaustive on limits (e.g. size ceilings or runtime), but well beyond the annotation baseline.

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 operation and result, then the usage trigger. The parenthetical IDS expansion earns its place by disambiguating an acronym, and there is no filler or repetition of the title.

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?

Because there is no output schema, the description carries the return-value burden and does so at an appropriate level — structure and failure detail are stated. Inputs, locality, and purpose are all covered for a three-parameter tool. It leaves open how sibling validate_ifc differs and any practical limits on large IFC files, which keeps it short of 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?

With 100% schema description coverage, the schema already documents all three parameters including accepted forms for ids and ifc and the maxFailures default. The description adds only an oblique reference to 'the first failures', which gestures at maxFailures without explaining its effect. Baseline 3 is the right ceiling when the schema does the heavy lifting.

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 pair: check an IFC model against an IDS file, with the standard spelled out (buildingSMART IDS 1.0). It also names the return shape, so the agent knows what it gets back. It does not differentiate itself from the sibling validate_ifc, which is the only gap.

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 concrete trigger: 'Use it when the user has an .ids file, or exchange requirements to verify a delivery against.' That is a clear context for selection. It falls short of explicit exclusions or a routing rule versus validate_ifc, so an agent facing both siblings must still infer which one applies.

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=false, so safety is covered; the description adds real behavioral value by disclosing the return shape (per-twin link and embed link, plus a builder link) and the data layers behind each twin. It does not contradict either annotation. It could still say more about link validity or whether the builder link requires auth, 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?

Three sentences, each doing work: catalog contents, return shape, and usage trigger, with the core resource front-loaded. The parenthetical data-source list is slightly long but is genuinely informative about what the twins show.

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 parameters and no output schema, the description carries the burden of describing returns, and it does so (links, embed links, builder link). Read-only behavior is confirmed by annotations. The only gap is that it does not say whether results are static/constant or whether the builder link is account-bound.

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?

The tool takes zero parameters, so the baseline is 4 and there is nothing for the description to compensate for. The description correctly implies a fixed, unfiltered catalog rather than suggesting any filtering options.

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 and resource ('List the ready-made city digital twins'), names the concrete instances (Barcelona, Helsinki, Tokyo), and enumerates what each entry contains (IFC models, OSM city, live open-data layers, links). No sibling tool in the list does anything similar, so an agent can distinguish it immediately.

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 an explicit trigger: 'Use it when the user asks for a digital twin demo or wants to start one,' and covers the adjacent builder use case. It stops short of naming an alternative tool or stating when not to use it, which keeps it below 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?

With readOnlyHint and openWorldHint=false already declared, the description adds value by disclosing the shape of the returned records (id, category, severity, default-enabled) and that the list covers the built-in rule catalog. It stops short of stating whether the list can change between calls or how large it is.

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 with no waste: the first states what is listed and what comes back, the second states why you would call it. The return-field list is front-loaded before the usage advice.

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 burden of describing return values — it does so by naming the four fields. Combined with read-only annotations and a zero-parameter schema, an agent has everything needed to call 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?

The tool takes zero parameters, so the baseline is 4; there is nothing the schema could document and the description correctly implies a parameterless full dump. It adds no misleading filter semantics.

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 and resource ('List every rule validate_ifc can run') and immediately enumerates the fields returned (id, category, severity, default-on). It also names the sibling tool whose rule set is being listed, so the agent can distinguish it from validate_ifc or check_ids.

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 two concrete use cases: pick rules to pass to validate_ifc, or explain what a rule checks. That is clear positive guidance, though it does not state when not to call it (e.g. that it is unnecessary if you already know the rule ids).

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=false, so the safety profile is covered. The description adds genuinely useful behavioral context — free, runs in the browser, no account required — which tells the agent there are no auth prerequisites. It does not say what the tool returns (a URL to present to the user) or what happens after invocation, which is the main behavioral gap.

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 usage sentence are appropriately front-loaded, but the middle is padded with device and export-format marketing detail ('phone, tablet, foldable or desktop... SVG, PSD, ORA or Blender') that does little to help an agent decide whether to call it. Roughly half the text could be cut without losing selection 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?

There is no output schema, so the description carries the burden of explaining the return value — yet it never states that the tool returns a link/URL that should be surfaced to the user. It also never mentions the openWorldHint=false caveat in relation to launching an external site. Adequate for a zero-parameter tool, but an agent is left guessing what it actually receives back.

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?

The tool takes zero parameters and the schema is empty, so there are no parameter semantics to explain; the baseline for a no-parameter tool applies. Nothing in the description misrepresents the input surface.

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 clause 'Link to the 3D sketch studio' names the resource and the action (hand back a link to a sketching studio), and the following clause clarifies what the studio does. An agent can distinguish it from model-inspection siblings like open_in_3d_viewer or read_dxf, though the description never explicitly contrasts itself with them.

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 a concrete triggering condition: 'Use it when the user wants to sketch an idea, mark up a design in 3D or make a concept drawing.' That is clear when-to-use guidance. It stops short of exclusions — nothing says when NOT to use it versus open_3d_viewer or open_drawings, so the 5 tier is not reached.

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 declare readOnlyHint and openWorldHint=false, so the description's disclosure that the tool 'builds a link' (i.e. returns a URL rather than data) is genuinely additive, as is the note that several URLs load as one federated scene. It omits caveats like link lifetime or whether opening requires an account, which keeps it at 4.

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 capability is front-loaded in the first sentence and the usage triggers follow. The middle sentence becomes a long inventory of pane features (calibrate, dimensions, export formats) that a caller selecting the tool does not strictly need, costing some tightness.

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 tool with no output schema, the description covers the essential unknowns: it produces a link, loads multiple models as a federated scene, and the browser must download the files. Missing details about the returned link's form or lifespan are minor.

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 the lang enum values and the public-URL constraint on models are already documented in the schema. The description adds nothing about parameter behaviour beyond that, so the 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 concrete verb+resource: it 'builds a link that opens IFC models with the drawings pane beside the 3D view'. That is specific enough to distinguish it from the sibling open_in_3d_viewer, though it never names the alternatives 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?

It gives explicit triggers — 'when the user wants a 2D plan, to check a drawing against the model, or to mark up a sheet' — which is clear usage context. It stops short of exclusions (e.g. when to use open_in_3d_viewer instead), so it is not 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?

The annotations only declare readOnlyHint and openWorldHint; the description adds behavior the agent could not otherwise know: the result is a URL plus an embeddable <iframe>, the tool does not launch a viewer itself, and the models must be public http(s) URLs because the browser does the download. It also lists what the viewer does after load (orbit, section, measure, validation), which frames the side effects that occur downstream.

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 action and output are front-loaded in the first sentence, with usage routing at the end. The parenthetical feature inventory ('orbit, section, measure, properties, validation with Health Score badge') and 'free IFC Viewer Online' branding are the least load-bearing parts and could be trimmed without losing 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 8-parameter tool with no output schema, the description supplies what is missing elsewhere: what is returned (a link and an iframe), that the tool is a link-builder rather than a launcher, and the public-URL constraint on inputs. Nothing an agent needs in order to call it correctly or explain the result to a user is absent.

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 maps several parameters to user-visible outcomes in plain language: 'drop them on the city map' (map), 'isolate a class' (isolate), 'pick a camera view' (view), 'add point clouds' (scans), and the drawings pane. It also reinforces the federated-scene behavior of the models array. Only the ui presets and validate are left entirely to the schema.

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 first sentence gives a specific verb and resource: 'Build a link that opens one or more public IFC files in the ... 3D viewer.' It is far more precise than a tautology, and it also states the output shape (a link plus an <iframe>). It never names a sibling tool, though, so the boundary with open_3d_sketch or open_drawings has to be inferred from the 'see, show, share or embed in 3D' framing.

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?

'Use it whenever the user wants to see, show, share or embed a model in 3D' gives a clear triggering condition, and the closing note that the link must be handed to the user (no window opens) sets an important usage expectation. There is no explicit when-not or named alternative, which keeps it below 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 readOnlyHint=true and openWorldHint=false; the description reinforces this with 'Runs locally' and adds supported format scope (ASCII, R12 to current) plus graceful DWG detection. The one gap is that the schema allows http(s) URLs, so the 'runs locally' framing does not mention that remote sources are fetched, which is a behavioral detail an agent would want.

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 short sentences, front-loaded with the capability and output contents, then usage, then the edge case. No sentence is redundant and the DWG caveat is placed last where it is least disruptive.

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 carries the burden of enumerating return values and does so thoroughly. The only shortfall is that it does not mention URL-based sources despite the schema permitting them, which is a small omission for a tool whose remote behavior is otherwise described as local.

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 `source` and `maxTexts` are already documented in the schema; baseline 3 applies. The description's mention of 'the text found on it (room names, labels, title block)' gives useful context on what maxTexts governs but adds no new syntax or limits beyond the schema.

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 (read/summarise a DXF drawing) and enumerates exactly what the summary contains: DXF version, units, per-layer entity counts, entity types, extents and extracted text. It is clearly distinguishable from the sibling open_drawings, which is named as the downstream placement step.

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 when to use it ('to tell what a drawing contains before placing it next to a model with open_drawings') and what to do when the input is unsupported ('DWG is detected but not read: ask the user to save it as DXF'). Both the positive case and the fallback are stated, leaving nothing to 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 and openWorldHint, so the safety profile is covered. The description adds genuinely useful context beyond that: the request goes directly from this machine to the broker (network egress, no intermediary), and results are flattened into a specific record shape. It does not discuss auth requirements or error behavior, keeping it at a 4.

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, front-loaded with the core action and resource, then the return shape, then the usage cue. Dense but each sentence carries information; the parenthetical broker list is slightly verbose but justified for disambiguation.

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 compensates by describing the flat record shape (id, type, attribute values with units, lat/lon, observedAt). Combined with full schema coverage for the 7 parameters, an agent has enough to call it correctly; only auth/error handling is unaddressed.

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 every parameter is already documented in the schema. The description only implicitly maps to the api parameter by mentioning NGSI-LD and NGSIv2, adding no syntax or format detail beyond the structured fields. 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?

States a specific verb and resource ('Read entities from a FIWARE context broker'), names the concrete broker implementations and protocols, and describes the returned shape. An agent can distinguish it from siblings like list_digital_twins or validate_ifc 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 says to use it 'to see what live data a broker offers before linking it to a model', which gives a clear triggering context. It does not name an alternative tool or state when not to use it, 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 readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing what a hit contains (an IFC download URL plus a 3D viewer link) and the licensing terms. It omits pagination behavior and result-count semantics for the 'limit' parameter, which keeps it short of 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?

Three sentences, front-loaded with the what/where and closing with the when-to-use rule. The parenthetical object-type list and format/license tags are dense but informative rather than filler; a truncation of the abbreviation list would be the only gain.

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 three-param, zero-required, read-only search tool with no output schema, the description covers purpose, domain scope, trigger condition, and the shape of returned hits. The only material gap is category discovery — the agent learns categories are 'listed in the answer' only after a first call.

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 67%: the 'query' parameter is well documented in-schema and 'category' is only hinted at ('the answer lists them'), while 'limit' has no description at all. The description restates the two search axes ('by words and category') but adds no enumeration of categories or syntax details, so it neither compensates for nor worsens the coverage gap.

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 names a specific verb and resource ('Search the Port de Barcelona BIM object library') and enumerates the domain contents (cranes, bollards, fenders, signs, buildings; IFC, CC BY 4.0). No sibling tool does library search, so an agent can route to it immediately.

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 trigger condition: 'Use it when the user needs port or maritime infrastructure objects for a model or twin.' It does not enumerate alternatives or when-not conditions (e.g. versus validate_ifc or open_in_3d_viewer), but the sibling set is functionally distinct enough that this is clear context without exclusion.

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?

Goes well beyond readOnlyHint/openWorldHint by declaring local execution and that 'the file is not uploaded anywhere' — a material privacy/behavior trait an agent would otherwise have to guess. It also previews the response shape (0–100 score, issue counts, highest-cost rules, first issues with fix-guide links), so the agent knows what comes back.

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 action and the return value, then privacy, then the trigger condition — a sensible order. Slightly long due to the rule-category enumeration, but each clause carries 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?

With no output schema, the description carries the return-value burden and does so adequately (score, counts, costly rules, sample issues, fix links). It is nearly complete for a read-only validation tool; missing only edge behavior such as unparsable files or runtime expectations.

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 three parameters are already documented, including the list_validation_rules cross-reference and the 'counts always cover all of them' note for maxIssues. The description adds little parameter-level meaning beyond restating that issues are truncated to 'the first issues'; 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?

States a specific verb and resource ('Check an IFC (BIM) model against the ... rule set') plus the distinguishing output, a Health Score. Adjacent siblings such as list_validation_rules and check_ids are clearly different activities, and the enumerated rule categories (schema, spatial structure, GlobalIds, ISO 19650) make the scope concrete.

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 explicit triggering conditions: 'Use it when the user asks whether a model is OK, what is wrong with it, or how good it is.' It also implicitly routes rule discovery to list_validation_rules via the 'rules' parameter. It stops short of naming when-not-to-use or contrasting itself with check_ids, so it is clear context rather than full routing guidance.

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