Sedna Genesis

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

Annotations already mark the tool as read-only and non-destructive; the description adds context about the tool being the official/authoritative source and establishes the required pre-call ordering. It does not contradict the annotations and contributes useful behavioral context beyond them.

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 purpose is front-loaded and the numbered guidelines are clearly structured, but the description is verbose for a zero-parameter tool. Several guidelines (e.g., fleet neutrality, customer-led decision, current-year default) are broader AI conduct rules rather than details specific to invoking Base_list.

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 parameterless, read-only reference tool with no output schema, the description is complete: it states what content is returned, how it is organized, and the exact workflow position relative to search_boats. An agent has enough information 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 has zero parameters, so the baseline is 4. The description appropriately avoids parameter discussion, and the empty input schema fully covers the parameter 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 description states a specific function: it provides the official Sedna rules and the complete list of available bases grouped by country. It also signals how this reference relates to the search workflow, distinguishing it from the sibling search and booking tools.

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 explicitly instructs the agent to always call Base_list before search_boats in order to find the exact base name. It also states the data-source constraint (Sedna-only, no internet searches), giving clear usage boundaries and naming the key alternative tool.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: all media comes through Sedna's CdnManager, missing CDN media is returned as an empty field and never replaced by a legacy DB URL, and the tool does not return date-specific prices/extras/availability. This gives the agent important expectations about data provenance and absence semantics.

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 well-structured and front-loaded with the core purpose, then flows into usage context, media handling, and exclusions. It is slightly long but every sentence earns its place by conveying critical routing and behavioral information. The only minor inefficiency is the somewhat dense enumeration of media fields, which is necessary for correct display.

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 tool with 3 parameters, 100% schema coverage, and no output schema, the description is quite complete. It covers what the tool returns, how to invoke it after search_boats, how to handle missing media, and what it does not return. The only gap is that it doesn't describe the exact structure of the response beyond field names, but since there is no output schema, the field enumeration partially compensates. It could also mention pagination or error behavior, but these are minor for this tool's scope.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters. The description adds meaningful context beyond the schema: id_boat must be copied exactly from search_boats (reinforcing the schema's 'Never guess it'), sheet_type=crewed is tied to crew and itinerary data, and the media fields returned are enumerated. This exceeds the baseline 3 by adding usage-oriented parameter 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 states a specific verb ('Return') and resource ('yacht details and CDN-backed public URLs for yacht media'), and explicitly distinguishes this tool from siblings by naming search_boats and booking_detail. It also enumerates the exact media fields returned, making the tool's purpose unmistakable.

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 explicitly says this is the primary tool to call after search_boats whenever the customer asks for photos, gallery, plans, videos, documents, layout, capacity, dimensions, equipment, description, crew, or itinerary. It also names booking_detail as the alternative for date-specific prices, extras, or availability, and instructs to copy id_boat exactly from search_boats. This is explicit when-to-use and when-not-to-use guidance.

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 declare readOnlyHint=false and destructiveHint=false but are minimal. The description adds meaningful behavior beyond them: the action re-prices before submitting, saved_extras is the authoritative verification for what was actually saved, and client contact fields are mandatory inputs. It still omits idempotency, duplicate-request behavior, and error handling for a mutation 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?

Front-loads the core action, then follows with the critical constraints in a logical order. Slightly redundant in places (the empty-list rule is also in the schema description) and the emphasis marker formatting is informal, but every sentence carries operational value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-param, 9-required mutation tool with no output schema, the description covers the submission flow, data-entry rules, and the verification signal (saved_extras) an agent needs. The gap is the six optional scheduling/payment parameters, which are undocumented in both the schema and the description and could cause incorrect omissions.

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%, and the description goes beyond it for the highest-risk parameter: selected_extras must repeat every chosen extra with the exact id_opt and quantity because the preview stores nothing, and an empty list is valid only when no extras were selected. It also clarifies that name/email/phone are required data. The optional arrival/departure/currency/port-pay params receive no explanation in either place.

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 ('Submits a request for a booking or a request for an option') and explicitly contrasts itself with the sibling booking_detail_mod as a stateless preview. An agent can distinguish this tool from the preview and from booking_detail 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?

Gives clear conditions and an alternative: booking_detail_mod is a preview and its selections are not stored, so this tool must be used to actually submit, and selected_extras must be repeated from that preview. It also mandates real client details and forbids guessing them. It does not, however, explain the booking-vs-option submission choice, which is left to the schema's mode param.

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

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

Annotations already cover read-only and non-destructive. The description adds behavioral nuance beyond that: it states that the tool returns date-specific content, that its images are only supplementary booking context, and that boat_details is the canonical media source. This prevents misuse and clarifies the data source, even though it doesn't describe fine-grained response details.

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 compact paragraph with each sentence earning its place: it states the result, gives the source requirement, excludes media-only calls, clarifies image usage, and provides the booking flow. It is not terse to the point of losing meaning, but it avoids irrelevant details. The structure is logical and front-loaded with the tool's purpose.

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 there is no output schema, the description tells the agent what to expect from the tool: availability, pricing, extras, and booking choices. It also covers the all-important interaction contract with search_boats and booking_detail_mod. It could better describe the output shape or error behavior, but for the agent's invocation it is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description says 'Use id_boat and id_tbf1 exactly as returned by search_boats', but the schema already states that for both parameters. With 100% schema coverage, the description adds no new parameter meaning beyond what the schema provides. It hints at 'date-specific' and 'selected yacht' but those map to existing params without adding format or semantics. Thus, the baseline 3 fits.

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: 'Return date-specific availability, pricing, extras and booking choices.' It also explicitly distinguishes itself from boat_details for media ('Do not call this tool only to see yacht photos or media'). This grounds the purpose and disambiguates it from siblings without needing to inspect 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?

The description gives explicit when-to-use and when-not-to-use guidance: it is 'for a selected yacht and charter period', and immediately tells the agent to call boat_details for media. It also directs the next step in the workflow: after modifications, use booking_detail_mod and its server-calculated totals. No room for ambiguity.

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 destructiveHint=false, and the description reinforces this with 'stateless price preview and does not save the selection.' It adds genuinely useful behavior beyond the annotations: the server is the single source of truth for prices and the LLM must never compute totals. It omits return-shape specifics, though for a preview tool the transparency is strong.

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 purpose and the pricing-authority warning are front-loaded, and each sentence carries actionable instruction. It is slightly longer than strictly necessary but no sentence is filler, so structure is efficient.

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 stateless preview tool with no output schema, the description tells the agent to present 'the complete updated summary returned by the server,' which compensates for the absent output schema. Combined with the source-of-truth and statelessness notes, an agent has enough to call it correctly; only the distinction from the booking_detail sibling is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents each parameter. The description nonetheless adds real meaning by explaining that id_boat and id_tbf1 must be copied from search_boats and that selected_extras, pax, currency, ports and payment options are the inputs to be sent. This provenance guidance is not present in 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+resource: 'Apply customer selections and return server-recalculated booking details,' which tells the agent this is a recalculation/preview step. It names sibling tools search_boats and booking_create as data sources and next step, but does not differentiate from the near-identical sibling 'booking_detail', leaving ambiguity about which variant to pick.

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 clear preconditions: copy id_boat and id_tbf1 from search_boats, and repeat the full selected_extras list in booking_create if the customer proceeds. It also clarifies this is a preview step that does not save. It stops short of stating when to choose this over the sibling booking_detail variant.

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

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

Annotations already declare the operation as read-only and non-destructive. The description adds useful context beyond annotations, such as 'indicative price' (implying non-binding estimates) and the constrained boat count of 2 to 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 description is compact and front-loaded with the main purpose, followed by a tight bullet list covering all parameters. No filler or redundant 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 annotations covering safety, an output schema covering return values, and the description covering purpose, parameter semantics, and constraints, the agent has everything needed to select and invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries full parameter documentation burden. It clearly explains boat_ids (2-4 ids), currency (EUR/USD/CNY, default EUR), and optional start/end dates with YYYY-MM-DD format—all in plain language 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?

The description uses the specific verb 'Compare' and names the exact resource ('2 to 4 boats') and the compared aspects ('specs, indicative price and availability'). This clearly distinguishes it from siblings like boat_details or search_boats.

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 makes the intended use obvious: comparing multiple boats with explicit constraints on boat count and optional availability window. It does not explicitly state when not to use it or name alternative tools, but the context is clear enough for selection.

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 description adds useful context by framing this as a static, authoritative rule set that applies to all conversations. It does not contradict the readOnly/openWorld/destructive annotations. It could be slightly more explicit that invoking this tool returns the rules as its output, but the content makes that clear.

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 front-loaded with its purpose and then delivers a numbered, actionable list. Each rule earns its place and there is no filler or redundant wording. The length is justified because the description is itself the substantive content of the readme 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?

The description provides complete operational context: ordering requirements, ID integrity rules, date clarification, media handling, and the distinction between search, details, and booking tools. Nothing needed for an agent to use the tool correctly is missing, and no output schema is required for a static rule set.

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 schema already covers this fully with an empty object. Per the baseline for no-parameter tools, the description does not need to add parameter meaning; it is compatible and does not introduce any confusion.

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 exactly what the tool provides: the official Sedna rules for public yacht-search conversations. It distinguishes itself from the operational sibling tools because it is a rule set, not an action. It is specific and not a tautology of the tool name.

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 explicitly says the rules govern every public yacht-search conversation, and the numbered rules directly tell the agent when to use which sibling tool, e.g., 'Call Base_list before search_boats', 'call boat_details', and 'Use booking_detail only for date-specific availability'. This is strong when-to-use guidance with concrete alternatives.

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 declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is already known. The description adds valuable behavioral context beyond that: results have passed Sedna planning/block and pricing checks, search results intentionally contain no images, and the agent is told to state count and fleets for large sets. No contradiction with 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?

Six sentences, each adding a distinct piece of information: purpose, prerequisite, result checks, large-set handling, no-images note, and follow-up tool routing. It is front-loaded with the core purpose and not overly verbose given the tool's complexity (13 params, no output schema).

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 what to do with results. It covers result counts, fleet names, and the absence of images, plus follow-up calls for media and pricing. It also handles the none-match case by suggesting alternative bases or dates. The description is sufficient for an agent to call the tool and interpret the high-level outcome.

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 baseline is 3. The description adds critical meaning beyond the schema: the 'base' parameter must come from Base_list, and 'start_date' plus 'nights' define the charter period that results are checked against. It also implies the use of optional filters (fleet, model, year) via the >10 result handling, though it doesn't detail each parameter.

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 ('Search'), a resource ('Sedna'), and a precise scope ('yachts available for the exact requested dates'). It also differentiates from siblings by referencing Base_list, boat_details, and booking_detail, making its role clear without ambiguity.

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 instructs to call Base_list first and use an official base name. It provides conditional behavior for result counts (more than 10, 10 or fewer, none) and explicitly routes the agent to boat_details for media and booking_detail for pricing, which clearly distinguishes from alternatives.

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