phasefolio

query_sec_deal_terms

Read-onlyIdempotent

Query SEC EDGAR deal-term extractions by indication, deal type, date range, confidence, and review state. Returns per-deal rows with source quotes and accession URLs for verification; aggregate engine medians use the separate backend aggregate function.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	Yes	Maximum rows to return, 1-500. Defaults to 100.
`since`	No	Optional inclusive effective_date lower bound in YYYY-MM-DD format.
`until`	No	Optional inclusive effective_date upper bound in YYYY-MM-DD format.
`deal_type`	No	Optional deal type filter.
`indication`	No	Optional indication filter, e.g. 'antimicrobial'.
`min_confidence`	Yes	Minimum extraction confidence threshold. Defaults to 0.5.
`include_needs_review`	Yes	Whether to include rows flagged needs_review. Defaults to true so admin users can see flags.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds that it returns per-deal rows with source quotes and accession URLs for verification, and that aggregate medians are not included here. This provides behavioral context about the output content and scope beyond what annotations state.

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

Conciseness5/5

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

Two sentences with no filler. The first sentence states the action and filter dimensions; the second adds return-value detail and a crucial exclusion about aggregate medians. Both sentences carry necessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, filters, return format, and an important scope limitation, making it well-rounded for a query tool. It doesn't detail output schema structure, but an output schema exists to handle that. The completeness is high given annotations and output schema.

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

Parameters3/5

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

Schema description coverage is 100%, so every parameter has an individual description in the schema. The description repeats filter categories but adds no additional parameter-level detail beyond what the schema already provides. Baseline 3 is appropriate when schema covers all parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's purpose as querying SEC EDGAR deal-term extractions with specific filters (indication, deal type, date range, confidence, review state). The verb 'Query' and resource 'SEC EDGAR deal-term extractions' are specific, distinguishing it from sibling tools like query_benchmarks or query_drug_risk.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by listing filter dimensions and noting that aggregate medians are handled by a separate backend aggregate function. This provides a partial when-not (for aggregates) but does not explicitly name sibling tools or provide when-to-use comparisons. No clear exclusions beyond the aggregate note.

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

All phasefolio tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Each tool targets a distinct entity or operation: get_* fetches specific objects, query_* searches datasets, list_scenarios enumerates, while triage_asset and verify_export are standalone actions. There is no functional overlap or ambiguity among the 13 tools.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in lowercase with underscores. The verbs (get, list, query, triage, verify) clearly indicate the action, and nouns identify the target. This uniform scheme makes the tool purpose predictable.

Tool Count5/5

With 13 tools, the server is well-scoped within the ideal 3–15 range. Each tool addresses a specific aspect of the drug-development analysis domain (project/scenario context, evidence, methodology, benchmarks, risk, landscape, SEC deals, dossier, verification, triage) without redundancy.

Completeness4/5

The read-side surface is thorough for the domain: projects, scenarios, evidence, methodology, benchmarks, drug risk, landscape, SEC deals, dossier, export verification, and triage are all covered. The only minor gap is the lack of a list_projects tool, but get_project can fetch a known project, providing a workaround.

Resources

Need Help?