GreenGo Partners

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

Annotations already declare readOnlyHint, idempotentHint and a closed-world scope, so the safety profile is covered. The description adds genuine value by scoping the payload to 'source links and GreenGo summaries only', but says nothing about the 20-item cap, ordering, or pagination.

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 no filler, and the retrieval axes are front-loaded ahead of the return-format note. Nothing wastes space, though the second sentence is terse to the point of being clipped.

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 no output schema the description does well to sketch the return ('source links and GreenGo summaries only'), and annotations cover safety. But for a 3-parameter tool with 0% schema coverage and all-optional inputs, the missing limit semantics and default-behavior guidance leave real gaps.

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 load; it clarifies 'topic' and interprets 'date' as the UTC digest date, which helps. However 'limit' is never mentioned and the enum values for topic are left entirely to 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 clear verb ('Read') and a specific resource ('published AI Builders Brief items'), plus the two filter axes (topic, UTC digest date). It is easily distinguishable from the listing-oriented siblings, though it never names 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?

'By topic or UTC digest date' implies the two retrieval modes, but there is no statement of when to prefer this over get_listing/search_listings, no exclusions, and no note on what happens if neither filter is supplied (all params optional).

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 readOnly, idempotent, and closed-world. The description adds real value beyond them: the data-visibility scope ('only public fields') and the failure mode for unknown or unpublished slugs.

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 no filler; the core action and its scope are front-loaded before the return/error note.

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-param read with no output schema, the description covers outcome scope and error behavior adequately. Minor gap: no mention of what fields constitute 'public fields' or rate/lookup caveats, but not essential for correct 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?

Schema coverage is 100% and the param is documented with a format pattern and example. The description adds only 'by slug', which the schema already conveys, so 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?

States a specific verb (fetch) and resource (one published GreenGo Partners listing) with the key qualifier 'published'. It implicitly separates itself from search_listings by emphasizing a single listing, though it doesn't explicitly name the sibling.

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 useful context that only public fields are returned and that unknown/unpublished slugs error, which implies usage conditions. However, it never explicitly says when to use this versus search_listings for discovery.

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, and openWorldHint=false, so safety and idempotency are covered. The description adds genuinely useful behavioral context beyond them: results are restricted to published listings and to public fields, which tells the agent no private/draft data or auth-gated content will appear. It stops short of disclosing pagination, ordering, or result 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, no filler. The primary action and filter surface are front-loaded, with the return-scope constraint following immediately.

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 no output schema, the description correctly carries the burden of describing what comes back ('public fields of published listings'), which is the key thing an agent needs. The remaining gap is operational: no mention of pagination, result caps, or ordering for what is inherently a list-returning search.

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%, including the non-obvious detail that max_price matches listings with at least one offer at or below it. The description merely restates the three filter dimensions and adds no format, default, or matching nuance beyond the schema, 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 (search), resource (published marketplace listings), and the exact filter dimensions (text, category, max price), plus the scope limit 'published' and 'public fields only'. It is clearly distinct from get_listing, which retrieves a single listing, though it never names that sibling 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?

Usage is only implied: the presence of filters suggests this is the discovery/browse entry point, and the 'published/public only' clause hints at what it will not return. There is no explicit statement of when to choose this over get_listing, no prerequisites, and no exclusions beyond the published-scope constraint.

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