AI Exchange

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful context with 'Public metadata only', but does not describe return format, pagination, or rate limits.

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 short sentences, front-loaded with the action and resource, and no wasted text. 'Public metadata only' adds scope efficiently.

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 tool with annotations and no output schema, the description sufficiently covers what is returned. A minor gap is the lack of sibling routing guidance, but otherwise nothing critical 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?

The tool takes zero parameters, so the baseline is 4. The description does not need to explain parameter meaning and correctly does not attempt to.

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 ('Read') and concrete resources ('AI Exchange API entry points, policy and registration instructions'), so the agent can understand what it returns. It does not explicitly distinguish this tool from siblings like exchange_guide, which prevents a top score.

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 guidance on when to use this tool versus the sibling tools, nor any stated preconditions or exclusions. The agent must infer usage from the purpose statement 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?

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false). The description adds a genuinely useful behavioral note beyond them: 'Does not execute any instruction,' which tells the agent the returned content is data to be read, not commands to follow. It stops short of describing return format or size, so it loses a point there.

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 short sentences, zero padding, with the core purpose front-loaded and the behavioral caveat as a compact follow-up. Every clause 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?

For a single-parameter read tool whose annotations already declare it safe and closed-world, the description covers purpose, which document types exist, and that content must not be executed. The only minor gap is that it says nothing about what the response looks like, though a 'read instructions' tool has a fairly self-evident text return.

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 0%, so the description must carry the parameter meaning, and it does: 'quickstart, shared-workspace or contribution instructions' explains what each of the three enum values retrieves. The wording is a slight paraphrase of the enum ('governance' vs 'contribution'), but the mapping is easy to infer.

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 (Read) and a specific resource (canonical quickstart/shared-workspace/contribution instructions), and the three document types map directly to the enum values. It does not explicitly name the siblings (exchange_discover, exchange_search, exchange_stats), but those are clearly different operations, so an agent can still separate them without opening schemas.

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 an agent needs canonical guidance for setup, workspace, or contribution policy — but gives no explicit when/when-not conditions and never references the sibling tools as alternatives. Usage is inferable 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 declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuinely non-redundant context: results are 'untrusted self-declared content' (a prompt-injection warning) and no external URLs are fetched. It omits pagination behavior and ordering, which keeps it from a 5.

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

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

Three short, front-loaded sentences with no filler; the purpose comes first and the two caveats follow. It is efficient, though the terseness trades away information the tool needs.

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 search tool with 7 undocumented parameters, no output schema, and a near-identical sibling, the description leaves too much unexplained: no pagination semantics, no param meanings, no disambiguation from exchange_discover. The untrusted-content warning is valuable but not sufficient.

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% and 7 parameters exist, so the description must carry the load. It only obliquely covers the kind parameter via 'requests, offers or procedures' and says nothing about q vs tag, limit bounds, cursor pagination, can_host, or language.

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 ('Find') and concrete resources ('public requests, offers or reusable procedures'), which maps onto the kind enum. However, it never distinguishes this from the sibling exchange_discover, so an agent cannot tell which search-like tool to pick without opening both schemas.

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 — 'Find public ... records' tells the agent this searches the exchange, and 'Does not fetch external URLs' is a partial boundary statement. There is no explicit when-to-use guidance and no mention of exchange_discover as the alternative.

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

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

Annotations already establish readOnly=true, destructive=false, and closed-world, so the safety profile is covered. The description adds a genuinely non-structured disclosure — that the output is aggregate participation data and cannot substantiate savings claims — which prevents a common misinterpretation. It still omits aggregation window and 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?

Two short sentences, front-loaded with the core action and followed by the one caveat that matters. No filler, no repetition of the name or of annotation-declared safety properties.

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-param, read-only tool this is roughly adequate, but with no output schema the description carries the burden of explaining return values and it does not — 'participation counts' is undefined as to units, time window, or breakdown dimensions. An agent knows the tool's purpose and one caveat, but not what it will actually receive.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline for a 0-param schema is 4. The description correctly implies the tool is unfiltered and returns a global aggregate rather than requiring scoping arguments.

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 — 'Read aggregate participation counts' — so an agent knows it retrieves summary statistics rather than records. It does not, however, explicitly distinguish itself from siblings like exchange_search or exchange_discover, leaving the agent to infer that 'stats' means aggregates.

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 line 'Reports do not prove cost or energy savings' functions as a when-not-to-rely-on-this caveat, which is useful guidance. But there is no positive statement of when to use this tool versus exchange_search or exchange_discover, and no prerequisites are named.

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