Invokary Platform Requirements

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description adds that results are grouped by topic and oriented toward differences, which is useful framing. It does not need to explain return values since an output schema exists, so 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?

Two tight sentences with the purpose front-loaded and the default behaviour placed last, which is the right ordering. The illustrative clause 'for example on authentication or on what a submission needs' is slightly padded but earns its place by concretizing 'topic'.

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 100% schema coverage, full annotations, an output schema, and no required parameters, the description carries only what the structured fields cannot: the comparative intent and the grouped output. Nothing essential for calling the tool is missing, though the category parameter's narrowing effect goes unexplained.

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

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

Schema description coverage is 100%, so both parameters are already documented, including the default platform set. The sentence about omitting platforms restates the schema default and the description never clarifies that 'category' narrows the comparison to a single topic, so it adds little beyond the schema baseline.

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 gives a specific verb (compare/sets side by side) and resource (platform requirements), plus the output shape ('grouped by topic... to show where they differ'). It implicitly separates itself from single-platform siblings like get_platform_requirements, but never names an alternative explicitly, so it stops 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?

'Leave platforms out to compare all four directories' documents the default invocation, which is real usage guidance. However, there is no statement of when to prefer this over get_platform_requirements or get_requirement, and no caveats about when comparison is not appropriate.

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, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered. The description adds that results carry sources, an evidence label and a last-checked date, which is useful context but the output schema already exists to describe the return 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?

Three sentences, front-loaded with the return contents before the filters and the enum values. The platform enumeration partly repeats the schema's enum, but the display-name mapping earns its place; no filler.

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

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

With an output schema present and annotations covering safety, the description only needs to cover filters and identification, which it does. A brief note on ordering or result size would make it airtight, but 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 description coverage is 100%, so baseline is 3, but the description adds value the schema does not: it maps the opaque platform ids to display names ('claude (Claude)', 'ecosystem (MCP specification)') and explains that category and productSurface are narrowing filters over the same result set.

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 a single platform's listing requirements, including the attached sources, evidence label and last-checked date. It is distinguishable from get_requirement (singular) and search_requirements, though it never explicitly contrasts itself with 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?

'Narrow the list to one topic (category) or one product surface' tells the agent how the optional filters are used, but there is no when-to-use-this-vs-alternatives guidance (e.g. vs search_requirements or compare_platforms). Usage is implied rather than stated.

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 readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds real behavioral context: sources and last-checked date are returned, and retired ids yield a retirement date plus the replacement requirement. That edge-case behavior is not visible in the annotations or input schema, though nothing beyond that is disclosed.

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, front-loaded with the core action and followed by the edge case. No filler.

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

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

With an output schema present, return shape need not be described, and the description still covers the primary path and the retired-id path. The only minor gap is the not-found case, which is not addressed but is partially implied by the retired-id handling.

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 id parameter documented, so the baseline would be 3. The description goes beyond the schema by giving a concrete id format example (claude.rule-annotations), which helps the agent construct a valid value.

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 ("Returns one requirement by its id") with a concrete example id, making it clearly distinct from the list/search siblings like search_requirements and get_platform_requirements. It even scopes the edge case of a single-item lookup vs. bulk retrieval.

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 phrase "by its id" implies the precondition (you must already know the id), which is the natural dividing line against search_requirements, but it never states that explicitly or names the alternative. Usage is inferable rather than spelled out.

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 read-only, idempotent, non-destructive behavior, so the bar is lower; the description adds ordering (most recently updated first) and that each note links to its full text. It does not mention limits or pagination, which is a minor residual gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that front-loads the resource and ordering, then the optional filters. No filler or repetition.

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 and full annotation coverage, the description needn't explain return values. It covers filtering, ordering, and the link to full text, leaving only pagination/size limits unstated.

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

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

Schema description coverage is 100%, so both `since` and `platform` are already documented in the schema with format and enum details. The description restates their meaning at a high level without adding syntax or edge-case guidance, matching the baseline 3.

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 (lists) and a precise resource (Invokary's dated notes on changes to platform submission rules), plus ordering and filter scope. It is clearly distinguishable from siblings like get_platform_requirements or list_platforms, which concern requirements/entities rather than change notes.

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 clear context for use: retrieving dated change notes, most-recent-first, optionally narrowed by platform or date. It does not explicitly name an alternative or state when not to use it, but the use case is unambiguous.

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 the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds useful context about what fields each record carries, but does not disclose anything beyond that – no rate limits, no pagination, no auth notes. Adequate given the annotation coverage, 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?

Two sentences, front-loaded with the resource and its enumeration, followed by the usage cue. Efficient, though the parenthetical list of platforms is slightly dense, but the extra detail earns its place by making the output shape concrete.

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 zero-parameter, read-only discovery tool with an output schema already present, the description covers everything an agent needs to know to call it: what it returns and why. Since the output schema exists, it needn't document return-value structure, and its framing of 'which ids the other tools take' closes the main gap by connecting this tool to its siblings.

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?

This tool has zero parameters, so the baseline is 4. The description correctly frames the tool as parameter-free discovery, and it compensates by enumerating the exact contents/labels of the returned records, which is helpful given there is nothing to parameterize.

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 (Lists) and resource (platforms) and names the exact dataset enumeration (Claude, ChatGPT, Cursor, Official MCP Registry). It also says what each record contains (directory, vendor, requirement count, topics, latest check date), which tells an agent precisely what this tool returns.

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 a clear use case: 'Use it to see what the dataset covers and which ids the other tools take.' That effectively positions this as the discovery/id-lookup entry point relative to siblings like get_platform_requirements and compare_platforms, though it does not name those siblings or state exclusions explicitly.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description's remaining additions ('up to 10 matches', 'best first', sources and check dates) largely duplicate the output schema, though the 10-result cap is a genuinely useful behavioral trait not captured elsewhere.

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, front-loaded with what the tool does and immediately followed by the result-shape cap. No filler and nothing buried.

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 search tool with an output schema, the description covers purpose, scope, and result limit. It stops short of mentioning ranking criteria or whether the 10-match cap is configurable, but nothing essential to invoking 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 the baseline is 3, but the description earns an extra point by giving concrete query examples ('privacy policy', 'OAuth', 'test cases') that illustrate what input shape works, and by phrasing the platform scoping as 'across every platform or within one', mirroring the platform enum.

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 ('Finds requirements') plus the matching scope ('whose text matches keywords or a question'). It implicitly separates itself from get_platform_requirements and get_requirement by being keyword-driven rather than platform- or ID-driven, but never names a sibling to make the boundary explicit.

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 reach for it (keyword/question lookup, optionally narrowed to one platform) but gives no explicit when-not guidance and does not name alternatives like get_requirement or get_platform_requirements. An agent can infer usage but must reason about the sibling boundary itself.

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