Open Medici Public Fellowship and Grant Search

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

Adds significant behavioral details beyond annotations: returns approved eligibility/funding facts, notes missing facts remain unknown, explains ranking signal is not personalized. No contradiction with readOnlyHint=true.

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 purpose, each sentence adds value with no repetition or fluff.

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 covering return values, description sufficiently covers input context. Minor gap: could mention slug requirement or locale default, but overall adequate for a simple tool.

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?

Description does not mention parameters; despite schema having 0% coverage and only 2 params, it fails to explain slug or locale, leaving agents to infer meaning from names alone.

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?

Description clearly states verb 'Get', resource 'one published public opportunity', and what it returns (cycles, source records, facts). Distinguishes from sibling tools like search_opportunities by focusing on a single item 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?

Provides context like 'before ranking or citing it' and warns about Open Medici ranking. However, lacks explicit guidance on when not to use or direct comparison with siblings.

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 indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds that it returns current database-backed values for one facet, and explains the meaning of empty results, which is consistent 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?

Concise single paragraph with a clear first sentence stating purpose, followed by usage guidance and a list of mappings. Slightly dense due to the mapping list, but effectively communicates necessary information without redundancy.

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 the presence of an output schema, the description does not need to explain return values. It sufficiently covers when to use the tool, how to interpret results, and maps filters to facets, providing complete context for effective use.

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 low (25%), but the description adds value by mapping filters to plural facet names, which extends beyond the schema's enum and description. However, it does not detail semantics for other parameters like q, limit, offset.

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 clearly states that the tool lists database-backed values for one public search facet, and distinguishes it from sibling tools like search_opportunities by specifying it should be used beforehand to avoid guessing taxonomy terms.

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 advises using this before search_opportunities instead of guessing taxonomy terms, and provides crucial interpretation guidance: an empty facet or absent user value means missing public coverage, not ineligibility.

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 indicate safe, read-only behavior. Description adds crucial context: search results are candidates only, must verify with get_opportunity; explains filter combination logic (OR within arrays, AND across fields). 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?

Two sentences packing essential information: purpose, strategy, filter logic, and post-search action. Every sentence earns its place, and key guidance is front-loaded.

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?

Despite complexity (32 parameters, many filters), the description covers the core behavioral rules and references sibling tools. Output schema exists, so return values are handled separately. Complete for effective agent use.

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 59%, so description carries some burden. It adds meaning beyond schema by explaining how filters combine and referencing list_filter_options for exact values. However, with 32 parameters, it doesn't detail each one individually, but the schema compensates with per-parameter descriptions.

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?

Clearly states the tool searches for published public fellowships, grants, scholarships, prizes, and funded residencies. Provides strategic guidance on how to search (start broad, avoid stacking filters) and distinguishes from siblings get_opportunity and list_filter_options by specifying this is for initial discovery.

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 advises to start with separate broad calls, not to stack sparse filters, and to use list_filter_options. Also directs to call get_opportunity before ranking or citing results. This gives strong 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.