Orion Celestia Intel

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

With no annotations provided, the description carries the transparency burden. It discloses that the brief includes anomaly signals with severity and provenance links, and explains that include_narrative toggles Orion's written prose. This gives a clear expectation of what the tool returns, despite not explicitly stating it is read-only or mentioning side effects.

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 two sentences, front-loaded with the main purpose and content, then a directed hint for the optional parameter. Every sentence is meaningful, with no filler or redundancy.

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 the tool's simplicity (one optional parameter, no output schema), the description thoroughly covers what the brief contains, how to trigger the narrative, and how it fits as the daily entry point. It is complete for an agent to understand the tool's scope and invocation.

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 schema already fully describes include_narrative, including its type and effect. The description adds only a brief reminder ('Set include_narrative for Orion's written prose summary'), which slightly clarifies the parameter's purpose but does not provide additional depth beyond the schema's description.

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 clearly states a specific verb ('get'), resource ('daily brief'), and content ('headline, anomaly signals with severity, key network metrics, and provenance links'). It differentiates from siblings by framing itself as the starting point for 'what is happening on Celestia today?', making it the obvious choice for a daily overview.

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 description provides clear context for when to use the tool ('Start here for...'), which is useful. However, it does not explicitly name alternatives or state when not to use it, only implicitly positioning it as the primary daily summary against sibling tools like get_signals or get_report.

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 no annotations, the description carries the transparency burden. It discloses the ordering (oldest to newest) and the 'one snapshot metric' constraint, but it does not mention response format, pagination, or error behavior. The read-only nature is implicit rather than explicit.

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 a single efficient sentence that front-loads the action and then provides the metric list. Every element is informative, with no wasted words.

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 tool with only two parameters and no output schema, the description covers the core purpose and available metrics. However, it does not specify the shape of the returned time series (e.g., array of date/value objects), which is a notable gap given there is no output schema to clarify it.

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 fully documents both parameters. The description adds slight context by clarifying 'time series' and listing valid metric values, but it does not substantially extend parameter semantics beyond the schema's own descriptions.

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 clearly states a specific action: retrieving a time series for a single snapshot metric from Orion's daily reports, ordered oldest to newest. It enumerates the available metrics, which distinguishes it from broader report-list tools like list_reports or search_reports.

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 description implies usage for historical metric retrieval but does not explicitly contrast with sibling tools like get_network_state (current state) or get_trends. The context 'across Orion's daily reports' provides a clear setting, but there are no exclusionary statements or alternative tool references.

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 no annotations, the description carries the full burden of behavioral disclosure. It states that the tool returns size, blob count, and last activity, which conveys a read-only nature and the kind of data to expect. However, it does not mention error behavior, such as what happens if the namespace_id is invalid or not found, nor does it explicitly state that the operation is read-only.

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 a single, concise sentence that front-loads the core purpose and includes essential context (hex format and source for the ID). Every phrase earns its place, with no redundant or vague wording.

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 simple getter with one parameter and no output schema, the description provides sufficient context: it names the parameter, its format, and the main return fields. It could be slightly more complete by stating the response format or explicitly noting not-found behavior, but these are minor gaps for such a straightforward tool.

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 schema description for namespace_id already explains that it is a hex string and suggests get_top_namespaces as a source, achieving 100% coverage. The tool description repeats this context (hex, get one from get_top_namespaces) but does not add substantially new parameter-level meaning, so the baseline score of 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 clearly states the tool's purpose: to retrieve details for a single Celestia namespace by namespace_id. It specifies the resource (namespace) and the scope (single), and distinguishes it from siblings like get_top_namespaces by focusing on one namespace's detail. The mention of fields (size, blob count, last activity) adds clarity.

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 description gives practical guidance by telling users to get a namespace_id from get_top_namespaces, which implies a workflow for when to use this tool. It does not explicitly mention when not to use it or name alternatives, but the context strongly implies it is for granular detail on a specific namespace.

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?

No annotations are provided, so the description must disclose behavioral traits. It notes that data comes from 'Orion's latest snapshot' (suggesting it may not be live) and includes 'provenance links.' However, it does not explicitly state that the operation is read-only (implied by 'get'), nor does it mention authentication, rate limits, or potential staleness beyond the snapshot wording. This is partial but not comprehensive.

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 a single, dense sentence that front-loads the core purpose and enumerates the specific metrics included. Every word adds value, with no filler or repetition. The structure is ideal for rapid parsing by an AI agent.

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 the tool's simplicity (no parameters, no output schema), the description is fairly complete: it lists the exact metrics returned and notes the inclusion of provenance links. It does not specify the response format (e.g., JSON structure), but the contents are well-covered. For a snapshot getter, this is adequate, though a note on format or update frequency would enhance completeness.

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 has zero parameters, and the input schema is empty. With no inputs to explain, the description does not need to add parameter semantics. The baseline of 4 applies here, as there is nothing to clarify and the description correctly focuses on outputs.

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 clearly states the tool's function: retrieving current Celestia mainnet metrics from a snapshot. It lists specific metrics (height, DA volume, fees, validators, etc.), which distinguishes it from sibling tools like get_metric_history or get_top_validators. The verb 'get' in the name and the explicit resource ('Celestia mainnet metrics') make the purpose unambiguous.

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 description establishes clear context: this tool provides a current snapshot of network metrics. It implies usage for obtaining an overview of Celestia's current state. It does not explicitly exclude alternatives or provide when-not-to-use guidance, but the context is sufficient for an agent to select this tool for current network state requests.

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?

No annotations are provided, so the description carries the full burden. It discloses the report contents (snapshot metrics, all signals, summary, provenance), which gives an idea of the response. However, it does not explicitly state read-only behavior, response format, or error handling, leaving some gaps.

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 one sentence, front-loaded with the core purpose ('Full Orion report for a specific date'), and then enumerates the contents. There is no wasted text.

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 simple retrieval tool with one parameter and no output schema, the description sufficiently conveys what the tool does and what data it returns. It could mention the response format explicitly, but the listed contents are enough for an agent to make a reasonable judgment.

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 input schema covers the single 'date' parameter with 100% coverage, including format and a pointer to list_reports. The description repeats the date format but adds no additional semantics beyond the schema, so the 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 'Full Orion report for a specific date' followed by the included contents (snapshot metrics, all signals, summary, provenance). This clearly identifies what the tool returns and differentiates it from siblings like get_signals (which likely returns only signals) or get_daily_brief (a brief, not a full report).

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 description implies when to use it: when you need the full report for a specific date. The schema's date property adds 'see list_reports for available dates', which hints at a workflow. However, there is no explicit comparison with alternatives like get_signals or get_daily_brief, so exclusions are absent.

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 no annotations, the description carries the full burden. It discloses the signal fields (type, severity, observed value vs rolling baseline, data source), the severity enum values, and the default latest-day behavior. It does not explicitly confirm read-only status, but the context and sibling get_* tools imply it, which is acceptable.

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 concise and front-loaded. The first sentence establishes the purpose, the second details the output fields, and the third mentions filtering. Every sentence contributes essential information with no redundancy or fluff.

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 tool with two optional parameters and no output schema, the description adequately explains the main output fields and default behavior. It covers the signal structure and severity levels but does not specify return format or pagination, though these are not critical for this simple read-only tool.

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%, with both parameters (date, min_severity) clearly described in the input schema. The description restates the default date and filtering capability but adds no new semantic meaning 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 clearly identifies the resource as anomaly/health signals from Orion, with a specific scope (per day, default latest). It distinguishes from sibling tools like get_trends or get_metric_history by focusing on severity levels (info|notable|critical) and rolling baseline comparisons.

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 description implies usage for retrieving anomaly/health signals, and mentions filtering by min_severity, but it does not explicitly state when to choose this tool over alternatives such as get_trends or get_daily_brief. No exclusions or alternative scenarios are provided.

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 no annotations, the description carries the full burden. It discloses that data is live and sorted by total blob size, but does not mention return format, pagination, or any side effects. For a read tool, this is moderately adequate but lacks depth.

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 zero waste, front-loading the primary purpose and adding a helpful clarifying detail. Every word earns its place.

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?

The tool has low complexity: one optional parameter, no output schema, and no annotations. The description covers the main purpose and data source. While it doesn't describe the response structure, the simplicity of the tool makes this acceptable.

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% as the 'limit' parameter has a clear description ('How many namespaces (default 10)'). The tool description adds no extra parameter context, so the baseline of 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 clearly states the verb and resource: 'Largest namespaces (rollups) on Celestia by total blob size' directly indicates what the tool returns. It distinguishes from siblings like get_top_validators (different resource) and get_namespace (singular focus).

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?

Provides context ('live from Celenium', 'who is posting the most data to the DA layer') implying when to use it, but does not explicitly mention when not to use it or point to alternative tools among the siblings.

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?

No annotations are present, so the description carries the behavioral burden. It discloses that data is live from Celenium and lists output fields, but does not explicitly state read-only nature, sorting details, or limitations beyond the stake ordering.

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 a single, compact sentence front-loaded with key information. It lists exactly what the tool returns and the data source, with no filler or redundancy.

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 simple tool with one optional parameter and no output schema, the description provides adequate context about the data source and included fields. However, it omits explicit return format and pagination behavior, leaving minor ambiguity.

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 schema fully documents the 'limit' parameter (min, max, default, description). The description adds no parameter-specific meaning, relying entirely on the schema's high coverage.

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 clearly identifies the tool as returning the largest Celestia validators by stake, with specific fields (moniker, stake, commission, jailed status). This distinguishes it from sibling tools like get_top_namespaces or get_trends.

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?

No guidance is provided on when to use this tool versus alternatives. The description lacks any 'use when' or 'not for' statements, leaving the agent to infer suitability from the name alone.

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 no annotations, the description bears the full burden of disclosure. It mentions the data source (Orion's daily snapshots) and the comparison periods (day-over-day, week-over-week), but it does not describe output details, potential edge cases, or any limitations. This is adequate but not 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?

The description is two sentences, tightly written, and front-loaded with the core purpose. The phrase 'what changed since yesterday / last week?' is a clear and memorable summary. No wasted words.

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 the simplicity of the tool (no parameters, no output schema, no annotations), the description provides sufficient context to select and invoke it. It covers purpose, usage, and a key data source detail. It is not overly verbose, and nothing critical is missing for a tool of this complexity.

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 has zero parameters, and the input schema is empty. According to the rubric, a 0-parameter tool receives a baseline of 4, and there is nothing for the description to compensate for. The description adds no parameter details because none exist.

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 clearly states it computes day-over-day and week-over-week changes for key Celestia metrics, which is a specific verb+resource. It also answers a concrete question ('what changed since yesterday / last week?'), distinguishing it from siblings like get_metric_history or get_network_state.

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 description gives clear context by framing the tool as answering 'what changed since yesterday / last week?', which tells the agent when to use it. However, it does not explicitly mention alternatives or exclusion conditions, so it stops 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?

With no annotations, the description provides useful behavioral context by specifying the output content (date + signal counts) and ordering (newest first). It does not mention side effects or auth, but the read-only nature of listing is implicitly clear, and the description adds meaningful disclosure beyond a simple 'list reports'.

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 a single sentence of 12 words, front-loaded with the tool's purpose. Every word contributes to clarifying what the tool returns and how it is ordered. No redundancy or 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 simple list tool with one optional parameter and no output schema, the description covers the essential return shape (date + signal counts) and ordering. It does not explicitly explain pagination or full report content absence, but the mention of 'index' implies metadata-only. This is adequate given the tool's simplicity.

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% (the only parameter 'limit' has a full description including default). The description does not elaborate on the parameter, but per the rubric, high schema coverage means the description need not compensate. 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 clearly states it provides an 'Index of Orion's daily Celestia reports' with content specified as 'date + signal counts' and ordering 'newest first'. This distinguishes it from siblings like 'get_report' (fetches a single report) and 'search_reports' (searches), making the tool's purpose unambiguous.

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 description implies the tool is for listing the report archive but does not explicitly state when to use it versus alternatives like 'search_reports' or 'get_report'. There is no 'when to use' or 'when not to use' guidance, leaving context 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It goes beyond generic phrasing by stating this is a 'plain keyword scan' with 'no LLM in the loop' and that results are 'verbatim from the archive.' It also discloses return grouping by date. It omits details like case sensitivity or no-match behavior, but the key behavioral traits are covered.

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 two sentences, front-loaded with the core action and scope, followed by an essential behavioral caveat about the no-LLM verbatim nature. Every sentence provides value without redundancy or excess length.

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 simple search tool with two well-documented parameters and no output schema, the description adequately covers the search scope, the return grouping, and the verbatim/no-LLM behavior. It lacks a few operational details (e.g., case sensitivity, handling of no matches) but is sufficient for correct tool selection and invocation.

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 schema already documents both parameters with 100% coverage, so the description's contribution is inherently supplementary. It adds meaningful context by specifying which fields the query searches (signal titles, details, types, metrics), which is not present in the schema. This enhances parameter understanding beyond the schema alone.

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 ('search') tied to a clear resource ('recent daily reports') and enumerates searchable fields (signal titles, details, types, metrics). This distinguishes it from sibling retrieval tools like get_report or list_reports by emphasizing keyword search and grouped-by-date results.

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 description clearly implies when to use the tool: when performing a keyword or phrase search across recent report content. It does not explicitly name alternatives or state when not to use it, but the 'keyword search' framing and scope ('recent daily reports') provide strong contextual guidance.

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