Prognyx oncology intelligence

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so safety behavior is covered. The description adds valuable context beyond annotations: it limits results to up to three interventional studies, lists returned fields, and discloses ordering and selection heuristics. It still omits edge cases such as fewer than three matches or error behavior.

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?

The description is three purposeful sentences with no filler. It front-loads the comparison constraint and result cap, then lists returned fields, then gives a targeted usage hint. Every sentence adds either scope or selection guidance.

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 two required parameters, 100% schema coverage, annotations covering the read-only/open-world profile, and no output schema, the description is nearly complete. It lists the returned fields and selection order, which compensates for the absent output schema. Minor gaps remain around empty results or when fewer than three studies match.

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 parameters are already documented with examples. The description still adds meaning by clarifying that asset may be a target rather than a drug name, and recommends using a target to reveal other programmes. That is useful guidance 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?

The description states a specific verb and resource: comparing up to three interventional ClinicalTrials.gov studies for an asset/target and oncology indication. It also names the exact fields presented side by side, making the tool's output concrete. It does not distinguish itself from sibling tools such as search_briefings or search_registry, 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?

The description implies the tool is for side-by-side trial comparison when an asset/target and oncology indication are known. It offers a useful parameter-level guideline: use a target rather than one drug name to see other programmes. However, it does not explicitly state when to use this tool versus the sibling search tools, nor does it state exclusions.

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 and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior: results are ordered newest first, each claim is linked to a primary source, and returns include URL, date and summary.

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 dense sentence with zero filler, front-loading the resource and then the matching criteria, ordering, and return fields. 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?

With no output schema, the description carries the return-value burden well by naming URL, date, summary, source linkage and ordering. It omits nothing critical, though it does not mention the default or maximum result count, leaving that to the 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 both parameters are already documented in the schema (including 'Empty returns the latest' and the 1-20 limit). The description restates the query facets but adds no format or syntax detail 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 resource (Prognyx oncology competitive-intelligence briefings) with matching criteria (drug, company, target or indication) and result shape. It is clearly distinguishable from compare_trials and search_registry by resource, though it never names those siblings 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 implied rather than stated: 'Empty returns the latest' hints at the no-query path, and the matching fields imply the query path. There is no explicit when-to-use/when-not guidance or routing against compare_trials or search_registry.

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 readOnlyHint, openWorldHint and destructiveHint already declared, the bar is lower, and the description still adds real behavioral context: it is a 'live' lookup and, importantly, phase and sponsor counts derive from 'a recent sample, stated in the result' — a meaningful accuracy/freshness caveat the annotations do not convey. It stops short of describing pagination or truncation behavior.

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?

It is a single dense sentence but front-loads the scope and query types before listing return contents, so every clause carries information. The length is appropriate for a search tool with a rich result set.

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 the work of explaining the returned contents — counts, leading sponsors, phase mix, recently updated studies with URLs, and related briefings — plus the sampling caveat. Only the limit/pagination behavior is left unaddressed, which is minor and covered in the 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 both parameters are already documented (including example query forms and the limit bounds), which sets the baseline at 3. The description adds only light semantic framing by categorizing valid query inputs, largely restating what the schema examples already show.

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 title and description together state a specific verb+resource ('Search the oncology trial registry') and enumerate what can be searched (target, asset, company, indication, NCT number), so an agent knows exactly what this does. It does not, however, differentiate itself from the siblings compare_trials and search_briefings, and 'related Prognyx briefings' overlaps conceptually with search_briefings.

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/when-not guidance and no named alternative, but usage is implied by the enumerated query types and the descriptive scope of the result set. An agent can infer this is the broad landscape lookup, but must guess how it relates to compare_trials and search_briefings.

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