d8a.tech

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

Beyond the readOnlyHint the description adds genuinely new behavioral context: it warns that notes and report titles are member-authored and must be treated as data rather than instructions, and it explains how to interpret the 'settings' and 'enforced' fields, including IP privacy. These are prompt-injection and interpretation safeguards that 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 usage instruction is front-loaded and each sentence carries distinct information, with no filler. The middle sentence is a long comma-separated inventory of return fields, which is dense but functional rather than padded.

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 read tool with an output schema and full annotation coverage, the description supplies everything an agent needs: when to call it, what comes back, and how to safely interpret member-authored text. Nothing material 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?

There is a single parameter and the schema already documents it at 100% coverage, including the pointer to d8a_list_properties. The description adds no further detail about the property_id argument, so the baseline of 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 names the resource (property context) and enumerates precisely what one call returns: timezone, today's date, goals with IDs, saved reports, dimension/metric IDs, notes, tracking protocol and URL, report availability, and query rules. That enumeration makes it clearly distinguishable from siblings like d8a_get_query_catalog or d8a_get_saved_report, which cover only slices of this payload.

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 this once per property before analysing it or touching its tracking" gives an explicit trigger and ordering constraint that an agent can act on without inference. It stops short of naming when-not conditions or pointing at alternative tools for narrower needs, so it falls just 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, but the description adds real operational context: unscoped calls page the entire catalog, unknown IDs are echoed back (reinforced by the schema), and descriptions=true trades listing size for meaning. It stops short of mentioning response size limits or rate behavior for full-catalog paging, so it is strong but 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 purpose, then the ID workflow, then the downstream rule — a sensible order with no filler. It is dense, packing multiple clauses into semicolon-chained sentences, which is efficient but slightly harder to scan than shorter discrete statements.

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 structure need not be restated, yet the description still characterizes what each catalog kind contains. With 8 parameters, a required property_id/kind pair, and cross-tool dependencies, everything an agent needs to call this correctly is present.

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, but the description earns more by explaining the interaction between ids and search (ids first, search as fallback, otherwise full paging) and by clarifying that goal metrics require a goal_id sourced from d8a_get_property_context. It does not add anything about limit/offset or the sources filter 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 ('check what a dimension, metric or transformation means and how to use it') and enumerates what each kind returns: value type, scopes, filter operators for dimensions; unit and parameters for metrics. This distinguishes it cleanly from the sibling run_* tools, which consume the IDs rather than explain 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?

Gives an explicit precondition ('before a query'), two retrieval modes ('Pass ids ... or search; without them it pages through the whole catalog'), and names the downstream consumers (d8a_run_query, d8a_run_funnel, d8a_run_paths) with the rule 'never guess'. It also routes to d8a_get_property_context for the IDs and goal_id, which is exactly the alternative-selection guidance an agent needs.

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 readOnlyHint/openWorldHint annotations, the description discloses the return contract (run_tool plus run_input deliberately without dates) and the error contract (issues returned instead of run_input, with the reason to repair). That is exactly the behavioral context an agent needs for a two-step workflow and is not derivable from the annotations.

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 key insight that this returns a tool reference rather than results, and every sentence contributes. The middle sentence is dense with semicolon-chained clauses and a nested example, which slightly taxes readability.

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-step dispatch tool with an output schema, the description still covers what an agent most needs: what comes back, why dates are omitted, how to proceed, and what happens when the saved report is broken. Nothing required 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 both parameters already document their source tools, so the schema carries the parameter burden. The description adds no per-parameter detail; its mentions of date range, preset, and compare refer to the downstream run_input rather than to this tool's inputs, 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?

The description states a specific verb and resource ('rerun a saved report') and immediately clarifies the actual mechanic: it does not execute the query but returns run_tool and run_input. Naming the three possible run_tool values (d8a_run_query, d8a_run_funnel, d8a_run_paths) cleanly separates it from those 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 gives an explicit sequence: add a date range or preset, optionally compare, then call run_tool, and notes the input may be adjusted first (e.g. adding a time_bucket column). It also covers the blocked case where issues prevent a run_input from being returned, so an agent knows both the happy and failure paths.

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 known. The description adds genuinely new behavior: the empty-call returns a topic index, and the overview topic carries method/consent/event-name/verification guidance. It doesn't describe response shape, but an output schema exists to cover 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?

The purpose and prerequisite are front-loaded, and the topic catalog is functional despite its length. Slightly dense in the middle, but every clause maps to a topic or a routing decision, so little is wasted.

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 read-only documentation retrieval tool with an output schema and fully documented parameters, the description supplies enough: the index behavior, the prerequisite topic, and sibling routing. Only the section-heading interaction with a topic (e.g., whether section requires topic) 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 coverage is 100%, so the baseline is 3, but the description earns extra by mapping real intents to topic IDs (web tracker, cookies and consent, cross-domain, GA4 duplication, GTM, Matomo, attribution, filtering, and the query/funnel/paths references) rather than leaving only 'Topic ID from the index'. The section parameter is only restated, not enriched.

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 resource (how-to knowledge on tracking and reporting) and makes clear it is a documentation/guide tool, not a query or mutation tool. It explicitly contrasts itself with d8a_get_tracking_install, so an agent can distinguish it from siblings without opening either 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?

It gives a concrete prerequisite ('Read topic "overview" before changing a site's tracking'), states the no-argument behavior ('Without a topic, lists them'), and routes property-specific snippet needs to d8a_get_tracking_install. That covers when to use, when not to, and the alternative.

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 read-only/openWorld safety profile, and the description adds context annotations cannot: the protocol is fixed per property, so only matching methods are returned, and GA4 duplication targets the existing GTM setup. The preserve-existing-analytics warning is a real operational constraint. It stops short of 5 since it doesn't describe the collector-URL format or output shape.

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 first sentence is front-loaded and serves well, but the parenthetical enumerating every method is dense and largely duplicates the enum in the schema. 'Keep existing analytics (do not remove GA4) unless the user asks' is worth its place, but the middle taxonomies are over-packed.

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 and 100% covered params, the remaining gap is guidance on what the returned snippets look like, which is acceptable. For a two-parameter read tool the description gives sufficient context to call it correctly and interpret protocol-dependent output.

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%, with the method enum and its documented defaults fully specified, so baseline 3 applies. The description does add useful semantics: method must match the property's protocol, and the GA4/Matomo options carry commitments like 'duplicate events' or 'replace on explicit request.'

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: returns the property's collector URL and ready-to-paste install snippets, broken out by protocol family (native tracker, GA4, Matomo). It's clearly distinguishable from d8a_get_tracking_guide (educational) and d8a_tracking_audit (verification) because it yields concrete install artifacts.

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 opening clause explicitly says to use it 'before adding or fixing tracking code on a site,' and the last sentence gives a policy directive: keep existing analytics unless the user asks. It doesn't name a sibling as the alternative (e.g., 'for conceptual guidance use d8a_get_tracking_guide'), so it stays at a clear-context, no-exclusion 4.

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 establish this as a read-only, closed-world operation, so the safety burden is low. The description adds useful context beyond that: what fields come back (id, name, tracking protocol, timezone), the sort order, and the downstream workflow via the id. It does not mention pagination behavior, though the schema fields hint at it.

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, each earning its place: discovery purpose, return contents/ordering, and the required follow-up workflow. The 'use this first' guidance is front-loaded.

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 only two optional parameters, a full output schema, and annotations covering safety, the description supplies everything an agent needs: what it returns, how it's ordered, and how its output feeds the rest of the toolset.

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 both limit and offset are fully documented in the schema, so the baseline is 3. The description adds no additional meaning about paging limits or offset semantics beyond what the schema already 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?

States a specific verb and resource ('find the analytics properties... of the connected account') and clarifies what a property is ('tracked websites or apps'). It also distinguishes itself from siblings by declaring itself the entry point before d8a_get_property_context.

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 sequencing guidance: 'Use this first' and 'Pass the id to every other tool, starting with d8a_get_property_context.' The agent knows exactly when to call this versus the other eleven sibling tools.

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 beyond the readOnlyHint/openWorldHint annotations by disclosing the ordering (most recently updated first), what the search field actually matches, and a prompt-injection caveat that saved report text is member-authored and should be treated as labels, not instructions. That untrusted-content warning is behaviorally important 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?

Two dense but purposeful sentences: purpose and ordering first, then the safety caveat, then the next action. No padding or redundant restatement of the tool name.

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?

Output schema exists so return shape need not be described, and the description supplies the discovery-to-detail workflow, result ordering, and the untrusted-content handling rule. 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 coverage is 100%, so limit, offset, search and property_id are all documented in the schema. The description only restates that search matches titles and descriptions, adding no new syntax or constraint detail. Baseline 3 applies 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 and resource ('find reports the team already saved for a property') and names the covered report types (tables, funnels, paths). It also distinguishes itself from the sibling d8a_get_saved_report, which returns one report's input, so an agent can route without opening either 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 gives the use case and the follow-up step: use this to discover saved reports, then call d8a_get_saved_report to get ready-to-run input. It stops short of stating when not to use it (e.g., ad-hoc queries via d8a_run_query), so it is clear but not exhaustive.

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, openWorldHint=false, and idempotentHint=false, so the description need not cover safety. It adds valuable behavioral context beyond annotations: the output includes per-step conversion, drop-off, timing, an optional breakdown, and comparison deltas expressed in percentage points. The description does not elaborate on rate limits or exactly what the output schema fields mean, but the output schema itself covers return values.

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 dense but front-loaded: it opens with the core purpose, then explains output metrics, comparison deltas, and step definition semantics. Every sentence adds information. It could be slightly more scannable with formatting, but it is efficient for the complexity of the 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?

Given a complex nested definition schema, an output schema, and high schema description coverage, the description is reasonably complete. It explains the funnel concept, references the tracking guide for deeper definition syntax, and mentions saved funnel reuse. It could optionally clarify the required property_id or how filters interact with steps, but the schema covers those fields.

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 83%, so the schema carries most parameter meaning. The description adds useful semantic guidance: it explains that steps are conditions on dimensions (e.g. the name dimension for event names) and that 'compare' runs the same request for an earlier period. It does not add details for preset, date_from, or date_to beyond what the schema already 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 uses a specific verb+resource ('measure conversion through ordered steps') and names concrete step examples (product view, add to cart, purchase). It clearly distinguishes this funnel tool from sibling query tools like d8a_run_query and d8a_run_paths by describing step-by-step conversion, drop-off, and timing.

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 when to use the tool ('to measure conversion through ordered steps') and gives prerequisite guidance ('read d8a_get_tracking_guide topic funnel-definition first, or start from a saved funnel's run_input'). It also explains the compare option's purpose. It does not explicitly exclude alternatives or name sibling tools like d8a_run_paths, leaving some routing implicit.

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 readOnlyHint=true annotation, it discloses that results preserve the journey graph (steps, edges, prefixes) along with truncation metadata and warnings, and clarifies that counts are journeys rather than users/sessions. That is meaningful behavioral context an agent could not infer from annotations or 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?

Front-loaded with the core purpose and example, then the constraint notes. It is dense and slightly run-on in a single paragraph, but every sentence (example, no-compare note, graph/truncation note, prerequisite, required-fields rule) carries 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?

With an output schema present, the description needn't explain return values, yet it still summarizes that counts are journeys and that truncation metadata/warnings accompany results — enough for an agent to interpret output. The prerequisite pointer to the tracking guide covers the deep nested definition semantics.

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 high (83%), so the baseline would be 3, but the description adds a genuinely useful constraint: every definition field except start, end and breakdown is required. That is a rule the schema technically encodes but is easy to miss across the large nested object.

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 ('see the journeys users or sessions take through events') and grounds it with a concrete example (page_view labelled by page, what follows a start item or leads to an end item). It is clearly distinguishable from a funnel/query tool by its start/end/breakdown framing, though it never names a sibling it replaces.

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 prerequisite ('Read d8a_get_tracking_guide topic paths-definition first') and an explicit when-not/alternative pattern ('No compare: run it twice with different dates'). It stops short of explicitly contrasting with d8a_run_funnel, which an agent might reasonably confuse this with.

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=true and openWorldHint=false already declaring safety, the description adds real behavioral detail: the compare mode joins groups with previous values and deltas, time series return as two separate series, and deltas are observational rather than causal. That is meaningful context an agent would otherwise have to infer.

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 'Use this to...' and the candidate question types, then semantics, then sibling routing at the end. Dense but each sentence carries information; the causality caution and label-presentation note are the only lines that could arguably be trimmed given the output schema exists.

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?

Output schema exists so return values need not be described, yet the description still covers the tricky compare-mode result shape. For an 11-parameter read tool it covers what is needed to call it correctly; only filtering/ordering behavior beyond the schema 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 coverage is 100%, so baseline is 3, and the description goes beyond it: columns use exact catalog IDs and can carry a time_bucket transformation, dates are inclusive YYYY-MM-DD in the property timezone or a preset. This gives practical invocation meaning the schema's field descriptions alone only partially convey.

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 sentence names a specific verb (answer questions with numbers) plus the concrete output shapes: dimension tables, time series with a time_bucket column, goal conversions, and period comparisons. It explicitly distinguishes itself from d8a_run_funnel and d8a_run_paths, so an agent can route without opening the 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 d8a_run_funnel for funnels and d8a_run_paths for journeys instead, giving the agent clear positive routing. It never states when not to use this tool for other cases (e.g. saved reports, catalog lookup), so it falls short of full when/when-not coverage.

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, openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond them: the tool returns a recipe rather than performing or completing an audit, which sets the agent's expectation for the response. It doesn't discuss result freshness or how the recipe should be executed, keeping 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 short sentences, zero filler. The primary use case is front-loaded, and the critical caveat about the return value follows immediately before the invocation note.

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 detail isn't required, and annotations carry the safety profile; the description supplies the one thing neither covers—that the output is a recipe, not a finished audit. The remaining gap is sibling disambiguation against d8a_get_tracking_guide and d8a_get_tracking_install.

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?

Zero-parameter tool, so the baseline is 4. The description confirms 'No arguments required,' which matches the empty schema with additionalProperties=false, leaving no ambiguity about how to invoke it.

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 and resource: it audits a website's tracking installation and diagnoses missing/duplicate events, and it explicitly frames the return as 'a read-only audit recipe, not a completed audit.' That output framing is the most valuable part. It does not, however, differentiate itself from close siblings like d8a_get_tracking_guide and d8a_get_tracking_install, which an agent would plausibly confuse it with.

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 opening clause gives a clear trigger ('when asked to audit a website's tracking installation or diagnose missing or duplicate events'), which is real when-to-use guidance. There is no when-not guidance and no named alternative for the overlapping tracking-guide/install siblings, so the routing decision is still partly left 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=true and openWorldHint=false. The description adds meaningful expectation-setting by saying it returns a recipe with 'selective Markdown follow-up notes, not completed analysis' — this prevents the agent from assuming it executes a full analysis. It does not discuss rate limits or side effects, but those are minimal for a read-only recipe tool.

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 tight sentences, front-loaded with the usage trigger and purpose, no filler or redundancy. Every sentence adds distinct 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?

An output schema exists, so the description needn't detail return values. The brief characterization of the output ('recipe with selective Markdown follow-up notes') is sufficient alongside the schema; only minor ambiguity remains about what the recipe includes.

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 description correctly states 'No arguments required', matching the schema. With no parameters to explain, the baseline is already high.

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 use case (weekly analytics review, prior-action follow-up, next priorities) and clarifies the output is a 'review recipe' rather than a completed analysis. This differentiates it from siblings like d8a_run_query and d8a_get_saved_report, though 'recipe' remains somewhat abstract.

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 triggers on requests for a weekly review, follow-up, or priorities. It doesn't name alternative tools to use instead, but the context is clear enough that an agent knows when this is the right entry point.

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