Clinical trials authorised by Health Canada.
Scored across 4 tools
condition_landscape and trial_detail are clearly distinct (aggregate landscape vs. single-protocol detail), but trial_search and trial_search_full perform the same keyword search and differ only in tier and result cap, so an agent must reason about FREE vs PRO and the 5 vs 200 limit to choose. The descriptions do help by labeling tiers and limits, but the boundaries are artificial rather than domain-driven.
All names are snake_case with a consistent topic_action shape (condition_landscape, trial_detail, trial_search), which is easy to scan. The only blemish is the '-_full' suffix variant for trial_search_full, which encodes a result cap rather than a distinct operation.
Four tools is compact and each maps to a recognizable job (landscape, detail, quick search, bulk search), so nothing feels bloated. It is on the thin side — the surface is essentially three operations with one duplicated as a pro variant.
The core lifecycle is covered: find trials by keyword, expand to a larger pro result set, drill into a protocol, and profile the competitive landscape. Gaps are minor — no lookup by sponsor/manufacturer or protocol-id-only batch detail, and no pagination or distinct-condition enumeration beyond the aggregate counts.
PRO. Trial counts per year and most common co-listed conditions for a keyword — competitive landscape.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | ||
| access_token | No | Subscriber token from /success (or Authorization: Bearer) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and discloses little. It implies a read-only aggregate and a subscription requirement via 'PRO', but says nothing about rate limits, result size, pagination, or what the counts actually represent (e.g., all trials vs. filtered subsets).
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?
One compact sentence with the outputs (trial counts, co-listed conditions) and the purpose front-loaded. Every clause carries information; only the terse 'PRO.' prefix is slightly cryptic.
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 simple two-parameter analytic tool with no output schema, the description conveys the shape of the return value (yearly counts plus condition pairs), which is the most important thing. It is still thin on auth/tier behavior and keyword semantics, leaving gaps an agent would need to probe at call time.
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 only 50%, with 'keyword' left completely undocumented in the schema. The description says counts are 'for a keyword' but gives no format guidance (free text vs. controlled vocabulary) or scope, so it does not compensate for the coverage gap.
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 concrete output: trial counts per year plus the most common co-listed conditions for a keyword, framed as a competitive landscape. That is specific enough to distinguish it from a plain trial search, though it never names the sibling tools (trial_search, trial_search_full) that an agent might otherwise pick.
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 or when-not-to-use guidance and no mention of alternatives. 'Competitive landscape' weakly implies aggregation/analysis rather than record lookup, but the agent must infer that against trial_search and trial_search_full on its own. 'PRO' signals a paid tier but not usage conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
PRO. Live detail for a protocol id: sponsor/manufacturer, drug products and study population.
| Name | Required | Description | Default |
|---|---|---|---|
| protocol_id | Yes | ||
| access_token | No | Subscriber token from /success (or Authorization: Bearer) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose two useful traits: the 'PRO' gate (subscriber tier) and that data is 'Live' (real-time). However it does not say what happens without a valid token, whether results are cached, or how errors surface.
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 compact sentences, front-loaded with the core purpose and followed by the fields returned. The leading 'PRO.' token is terse to the point of being cryptic but does not waste space.
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 simple two-parameter lookup with no output schema, enumerating the returned fields is valuable context. Still missing are how to obtain a protocol id, what the PRO gate means operationally, and failure behavior, which leaves gaps for an agent to call it confidently.
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 50%: access_token is documented in the schema but protocol_id is bare. The description only restates that a protocol id is the key and does not clarify its format, source (e.g. from trial_search), or behavior for invalid ids, so it only partially compensates for the undocumented parameter.
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 ('Live detail for a protocol id') and lists the returnable fields (sponsor/manufacturer, drug products, study population). The word 'detail' implicitly contrasts with the sibling 'trial_search' tools, though no sibling is named 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?
There is no explicit when-to-use guidance or reference to alternatives like trial_search or trial_search_full. At best it is implied that you must already hold a protocol id (presumably from a search), but the description never says so or explains prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
FREE. Health Canada-authorised clinical trials for a condition or drug keyword — newest 5.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden and does well: it discloses cost ('FREE'), the authoritative data source (Health Canada-authorised), the result limit (5), and the sort order (newest first). It omits whether keyword matching is exact or partial and says nothing about auth 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?
One compact sentence with the cost signal front-loaded and the scope, source, and limit packed in without waste.
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 one-parameter, no-output-schema, no-annotation tool, the definition covers cost, source, count, and ordering. The remaining gap is how results are selected and matched, which matters somewhat for a search 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?
Schema coverage is 0% for the single keyword parameter, so the description must compensate. It does clarify that the keyword may be either a condition or a drug name, which the bare 'string' schema does not, but adds no detail on matching behavior, brand vs generic names, or partial terms.
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: Health Canada-authorised clinical trials searched by condition or drug keyword, capped at the newest 5. The result cap implicitly separates it from trial_search_full, though the sibling is never named.
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 a use context ('for a condition or drug keyword') but never states when to prefer trial_search_full or trial_detail. The 'newest 5' cap hints at the alternative without saying so explicitly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
PRO. Up to 200 trials for a keyword, optionally started since a date.
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | ||
| keyword | No | ||
| access_token | No | Subscriber token from /success (or Authorization: Bearer) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose two real behavioral traits — a hard 200-result cap and start-date-based filtering — but says nothing about pagination/truncation behavior, authentication/subscription requirements, or error conditions for a tool whose access_token implies gated access.
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 compact sentence plus the 'PRO' marker; nothing is padded. The front-loaded 'PRO' is cryptic rather than informative, which slightly undercuts the front-loading benefit.
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?
No annotations, no output schema, and only one of three parameters documented in the schema. For a search tool that can return 200 records, the description should say something about result shape, truncation, or required credentials; all of it 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 33% (only access_token is documented), so the description must compensate. It does clarify that 'keyword' drives the search and that 'since' filters on trial start date, which adds meaning beyond the bare string types, but format expectations for 'since' and keyword matching rules remain unstated.
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 (search trials) with scope cues: 200-result cap and an optional start-date filter. The 'PRO' prefix signals a premium-tier variant, but it never explicitly contrasts with the sibling trial_search, leaving the distinction implicit.
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?
No statement of when to use this instead of trial_search, trial_detail, or condition_landscape. The only usage hint is the opaque 'PRO' tag, which does not tell the agent whether a subscription requirement or a different result set is the deciding factor.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
condition_landscapetrial_detailtrial_searchtrial_search_fullHealth Canada Drug Product Database (fleet #522).
WHO ICTRP — the International Clinical Trials Registry Platform search portal…
Clinical trial search and status from ClinicalTrials.gov
ANZCTR — the Australian New Zealand Clinical Trials Registry (anzctr.org.au, run by the NHMRC…
Add one secure layer between your agents and this server.