Disc Golf England (EDGA)

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

With no annotations, the description carries the full burden. It usefully discloses the output medium (ready-to-adopt .docx), the interactive placeholder-prompting flow, and that it accepts or requests customisation variables. It omits delivery details (file path, download vs. inline), any permission/auth requirements, and whether generation is idempotent or rate-limited.

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, no padding, and the purpose is front-loaded before the interaction/variable mechanics. Every clause earns its place by adding scope, output format, or invocation behavior.

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 no annotations and no output schema, the description covers purpose, output type, and the variable-driven generation flow reasonably well, and the 14-value topic enum is exhaustively enumerated in the schema. Remaining gaps (how the .docx is returned, disclaimer enforcement) are modest.

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 topic, variables, and include_disclaimers thoroughly. The description adds the example keys (club_name, adoption_date, welfare_officer) and restates the omission-fallback behavior, but adds no syntax or format detail beyond the schema. 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 names a specific verb (Retrieves) plus a concrete resource set (EDGA model templates, constitutional clauses, administrative checklists) and a tightly bounded domain (volunteer-led disc golf clubs in England). It is clearly distinguishable from siblings like search_courses or get_edga_tour, though it never explicitly names an alternative to route against.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the agent can infer this is for starting/registering a new club, and the description clarifies the variable-filling interaction. There is no statement of when NOT to use it or which sibling covers related governance lookups (e.g. get_governance_policy).

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 and does meaningful work: it discloses that the output is advisory, includes source links, evidence dates and verification limits, and that numerical buffers, budgets and case-study claims are not an authoritative safety standard. That epistemic framing is exactly the kind of context an agent needs, though it never states explicitly that the call is a read-only operation.

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 tight sentences with the core purpose front-loaded and the caveat second. Every clause carries information, though the list of caveats ('buffers, budgets and case-study claims') is slightly dense.

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 retrieval tool with fully documented parameters and no output schema, the description covers purpose, return content (source links, evidence dates, verification limits) and a critical trust limitation. An agent knows what it gets and how far to trust it; only the read-only nature and sibling routing are left implicit.

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

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

Schema description coverage is 100% with enums on three of four parameters, so every parameter is already documented structurally. The description adds no parameter-level detail (e.g. how hole_count or landowner_type shape the returned guidance), 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?

States a specific verb ('Retrieves') and resource ('advisory EDGA course planning guidance') with a clear scope modifier ('advisory'). It is distinguishable from retrieval siblings like get_governance_policy, though it does not draw an explicit line against the closely related get_club_starter_guidance.

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 never states when to use this tool versus the alternatives (get_club_starter_guidance, get_governance_policy, search_courses). Usage must be inferred entirely from the tool name and the word '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?

With no annotations, the description must carry the full behavioral burden. It discloses the authoritative source (Tjing), that standings are 'real-time,' and the restriction to configured competitions — useful context — but says nothing about permissions, error behavior, or limits on the standings/stage_id relationship.

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?

A single, well-front-loaded sentence with the primary resource named first and the scoping constraint trailing. No filler or redundancy, though it crams several distinct data types into one long clause.

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 retrieval tool with zero required parameters and full schema coverage, the description adequately conveys the domain and the kinds of data returned. Without an output schema, more detail on return shape would help, but the enumerated content types cover the essentials.

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 each enum value (schedule, standings, divisions, seasons, stats) is fully documented in the schema, so the baseline is 3. The description's enumeration of content types loosely overlaps the view options but adds no syntax or format detail 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 ('Retrieves') and enumerates the exact resources (EDGA Tour schedules, stage dates, divisions, season highlights, standings) plus a data source (Tjing). The scope restriction to 'configured EDGA Tour competitions' makes it clearly distinguishable from the governance/course siblings, though it does not name them explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance. The closest thing is the constraint 'strictly restricted to configured EDGA Tour competitions,' which tells the agent the tool's domain boundary but not when to prefer it over alternatives or what prerequisites apply.

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 does disclose the return payload (full text, metadata, statutory basis, status, download URLs, sections), which is genuinely useful, but says nothing about auth requirements, not-found behavior, or rate limits for a read 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?

A single front-loaded sentence that lists the return contents without waste. The parenthetical '(PDF/DOCX)' is the only mild embellishment and it is informative.

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

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

For a two-parameter read tool with no output schema, the description usefully enumerates what comes back, compensating for the absent output schema. Missing only call-failure and permission context, which keeps it from a 5.

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

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

Schema description coverage is 100%, with the slug examples and the format enum (markdown/text/summary) fully documented in the schema. The description adds no parameter syntax or format behavior beyond that, 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?

States a specific verb (Retrieve) and resource (a specific EDGA governance policy or standard), and enumerates what is returned. The word 'specific' implicitly distinguishes it from list_governance_policies, but no sibling is named explicitly, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of prerequisites (e.g. needing a valid slug), and no routing to alternatives such as list_governance_policies for discovery. The agent must infer usage entirely.

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 behavioral burden, and it does disclose the returned attributes (slug, title, status, review date, statutory basis, URL), which matters because there is no output schema. However, it says nothing about read-only safety, result size, ordering, or whether the list is paginated.

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?

A single front-loaded sentence with no padding. The field enumeration is dense but earns its place given the absence of an 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?

For a one-optional-parameter read tool, the description covers the resource, the covered policy types, and the return fields, which substitutes for the missing output schema. Pagination and result-size expectations are the only notable 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 description coverage is 100%, with the single 'status' enum fully documented (all/current/draft), so the baseline of 3 applies. The description mentions 'status' only as a returned field, not as a filter, adding no semantic value 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 ('List all official EDGA governance policies, codes of conduct, and standards') and enumerates the fields returned. The verb 'List all' implicitly separates it from the singular get_governance_policy sibling, though that sibling is never named, so the differentiation is left to the reader.

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?

There is no when-to-use guidance, no prerequisites, and no mention of the alternative get_governance_policy for fetching a single policy. The agent must infer that this is the enumeration path from the tool 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 carries the full behavioral burden. It usefully discloses data provenance and freshness ('supplied live by the independent DiscGolfAPI service', 'EDGA does not own or control these records'), which signals the records are third-party and may change. It does not, however, describe rate limits, error/empty-result behavior, or result pagination behavior beyond what the schema's offset/limit already imply.

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 with the core action front-loaded and the two search modes stated up front. The provenance sentence is justified for a third-party data source, though it is slightly more attribution context than strictly needed for tool selection.

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 nine-parameter search tool with no output schema and no annotations, the description covers the request side adequately but says nothing about what is returned (result fields, ordering, distance values for coordinate searches, or how offset/limit interact with has-more results). The gap is real, though most of the input complexity is absorbed by a fully documented schema.

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 nine parameters, including filter semantics like null exclusion for is_free and is_18_holes and the pairing requirement for latitude/longitude. The description adds no per-parameter syntax or format detail beyond the schema, 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?

States a concrete verb and resource ('Searches public course records') and goes further by naming the two distinct operating modes: keyword matching against recorded names/localities and nearest-course lookup from coordinates. No sibling tool performs course search, so the purpose is unambiguous against get_edga_tour, get_governance_policy, and the guidance/framework 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 makes the when-to-use conditions clear by distinguishing a keyword/locality search from a coordinate-based nearest search, which tells the agent which parameter family to populate. It stops short of explicit exclusions or named alternatives, so it earns a 4 rather than a 5.

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