Estimate hours and cost of systematic or literature reviews: screening and full-text reading.
Scored across 1 tool
With only one tool, there is no possibility of misselection or overlap. Its purpose is clearly stated and distinct within the server's surface.
The single tool follows a clear verb_noun snake_case convention (estimate_literature_review_time). No competing naming styles exist to create confusion.
A single tool is thin for a calculation domain; there is no way to request partial breakdowns or alternative scopes. The narrow purpose makes one tool defensible, but it sits at the borderline of under-scoped surfaces.
The tool covers the core computation (screening/reading hours, stage shares, double-screening overhead, cost), but there are notable gaps such as exposing assumptions, returning structured breakdowns, or handling non-BRL currencies. Agents can work around this only by inferring outputs from a single flat result.
Calculates the hours spent screening titles and abstracts and reading full texts, per review and per year, the share of each stage, the extra effort of double screening and, when an hourly cost is given, the yearly cost in Brazilian reais.
| Name | Required | Description | Default |
|---|---|---|---|
| review_type | Yes | Kind of review. | |
| records_found | Yes | Records returned by the database search of one review. | |
| full_texts_read | Yes | Full texts read per review. | |
| hourly_cost_brl | No | Optional cost of one hour of work, in BRL. | |
| reviews_per_year | Yes | Reviews the group runs per year. | |
| reviewers_per_record | Yes | How many people screen each record. | |
| minutes_per_full_text | Yes | Minutes to read and extract one full text. | |
| minutes_per_record_screening | Yes | Minutes to screen one title and abstract. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds genuine behavioral detail about what is computed: per-review and per-year hours, stage shares, the extra effort of double screening, and cost only 'when an hourly cost is given'. It does not disclose assumptions, defaults, or units of rounding.
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 front-loaded sentence with the core action first and outputs enumerated after. Dense but no filler; the trailing Brazilian-reais clause earns its place by fixing the currency.
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?
There is no output schema, so describing the returned quantities is exactly what this description must do, and it does so comprehensively: stage hours, per-review and per-year totals, stage shares, double-screening overhead, and conditional cost. An agent can judge from the description alone whether the result answers its question.
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%, so every parameter and its bounds are already documented. The description adds modest meaning by tying hourly_cost_brl to the optional cost output and reviewers_per_record to 'double screening', but it explains no syntax or interaction beyond that. Baseline 3 is correct.
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?
Opens with a specific verb and resource — 'Calculates the hours spent screening titles and abstracts and reading full texts' — and then enumerates the computed outputs. The purpose is unambiguous, though the enumeration crowds out a single crisp statement of intent.
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 explicit when-to-use or when-not-to-use guidance, and no prerequisites or alternatives named. Usage is only implied by the output list (a planning/estimation aid). With no sibling tools the cost of this gap is low, but the guidance itself is absent.
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.
estimate_literature_review_timeSystematic medical reviews and evidence-based healthcare research
Estimate software projects by independent expert judgement, with your team and an AI estimator.
Pay-per-call ($0.25 USDC) project cost estimator: modules + cheapest model mix that clears quality.
Scholarly literature search across nine sources
Add one secure layer between your agents and this server.