FundScout

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: it uses the investment-date NAV or the next available NAV date, defaults valuation to the latest NAV, and explicitly excludes stamp duty, exit load, and tax while noting it cannot project future returns.

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 dense sentences, front-loaded with the core calculation and scope, then the mechanic and the exclusions. No filler; every clause carries information.

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 read-only calculation tool with full schema coverage and no output schema, the description covers inputs semantics, the calculation method, the default valuation behavior, and the limitations (no tax/load/stamp duty, no future projection). Nothing an agent needs to invoke it correctly 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 100%, so the baseline is already 3. The description adds calculation semantics the schema does not: units are bought at the NAV on the investment date (or the next NAV date if unavailable), and end_date defaults to the latest NAV, clarifying the optional parameter's behavior.

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 (calculate) and resource (lumpsum investment value in one Indian mutual fund scheme), and explains the mechanism (units at NAV on investment date, value at latest/chosen end date, gain, return, CAGR). Clearly distinguishable from siblings like calculate_sip_returns and compare_funds.

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 frames the use case as 'if I had invested X on date Y' questions, which anchors when to reach for it, and the scheme_code description points to search_mutual_funds as the source. It does not, however, explicitly say to use calculate_sip_returns for recurring investments, so the sibling routing is left partly implicit.

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/idempotentHint/non-destructive, and the description does not contradict them. Beyond that it discloses genuinely useful behavior the annotations cannot convey: NAV-on-due-date with holiday rollover, the full return payload (instalments, invested, units, current value, absolute gain, XIRR, year-by-year summary), step-up support, and explicit exclusions (stamp duty, exit load, tax, no future projection).

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?

Purpose is front-loaded in the first clause, followed by mechanics, then output shape, then limitations. No redundant sentences and no repetition of what the schema or annotations already state.

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 compensates by enumerating the returned metrics, and it discloses pricing behavior and model limitations for a 5-parameter simulation tool. Nothing material an agent needs to call it correctly or interpret the result 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 description coverage is 100%, so the baseline is 3, but the description adds real semantics beyond the schema: the holiday-rollover rule that governs how start_date/end_date instalments are priced, and confirmation that annual_step_up_pct drives a yearly increase in the SIP amount. The remaining parameters (scheme_code, monthly_amount) are already fully documented in-schema and add nothing in the text.

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 precise verb (simulate) and resource (monthly SIP in one Indian mutual fund scheme) and explains the core mechanics: each instalment buys units at the NAV on its due date or the next NAV date after a holiday. The word 'monthly SIP' inherently separates it from the sibling calculate_lumpsum_returns, which an agent can distinguish without opening either schema.

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?

Gives an explicit usage cue: "Use for 'what would my SIP be worth' questions." It also carves out scope limits (ignores stamp duty, exit load and tax; can't project future returns), which effectively tells the agent when not to rely on it. It stops short of naming the alternative tool (calculate_lumpsum_returns) for one-time investments, so it is clear context rather than full when/when-not routing.

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 supply readOnly/idempotent/non-destructive, so the bar is lower, yet the description still adds real behavioral context: all metrics are computed to the same as-of date, and it flags mixed categories, Direct vs Regular plans and IDCW options. It doesn't cover error handling for invalid codes, but the added traits are substantive.

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 tight sentences, front-loaded with the action, scope and input, then the returned metrics, then when-to-use and the negative scope. No filler or repetition of the title.

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 compensates by enumerating the returned metrics (NAV, category, plan, option, 1M/3M/6M/1Y returns, 3Y/5Y/10Y CAGR) and the same as-of date guarantee. Combined with 100% schema coverage, an agent has everything needed to call it correctly.

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% and there is only one parameter, so the schema does the heavy lifting (minItems/maxItems, 6-digit code format). The description's '2 to 5' and 'by AMFI scheme code' restate schema constraints rather than adding new syntax or format meaning.

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 (Compare) plus resource (mutual fund schemes), the exact input identifier (AMFI scheme code), the cardinality (2 to 5), and precisely which fields are returned. It is immediately distinguishable from get_fund_nav (single NAV) and search_mutual_funds (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?

'Use when the user wants to compare funds' past performance' gives a clear triggering condition, and 'It does not rank or recommend funds' sets a useful exclusion. It stops short of naming the sibling tools (e.g., use get_fund_nav for a single fund), so routing is inferred rather than explicit.

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 readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely useful context beyond them: it discloses that returns are computed from NAVs only and exclude exit load and tax, which materially affects how the agent should present the numbers. It does not mention pagination or error behavior, keeping it out of the top band.

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?

Front-loaded with the core action, and every clause earns its place by either scoping the lookup or enumerating the payload. The long enumeration in sentence one is dense but functional, not padding.

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 the description usefully enumerates the return fields (NAV, returns, CAGR, 52-week range, plan/option). Combined with the tax/exit-load caveat, an agent has enough to call and interpret the tool, though it omits any note on data staleness or failure modes.

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?

With one parameter at 100% schema coverage, the schema already documents the 6-digit AMFI scheme code and points to search_mutual_funds as its source. The description's mention of 'AMFI scheme code' repeats rather than extends that, so the baseline 3 is appropriate.

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 ('Get the latest official NAV and NAV date for one Indian mutual fund scheme by AMFI scheme code') and enumerates the returned metrics, so the agent knows exactly what this does. It is clearly a NAV/returns lookup rather than a calculator, but it never names the sibling tools (calculate_lumpsum_returns, compare_funds) to sharpen the distinction, so it falls short of the top band.

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?

'Use when the user asks for a fund's NAV today or its returns' gives a concrete trigger condition. There is no when-not guidance and no explicit routing to the calculate_* or compare_funds siblings, which would be the natural alternatives for return computations.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld). Beyond that, the description discloses two non-obvious behaviors: inactive schemes (closed/matured/merged) are hidden by default, and coverage is limited to AMFI's NAV dataset. It does not mention rate limits or result-ordering behavior, but adds real value over the 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?

Four sentences, front-loaded with what is searchable and what comes back, then workflow guidance, then the inactive-scheme caveat and data-scope boundary. Dense but each clause carries information; no filler.

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 the description usefully enumerates the returned fields (AMFI scheme code, plan, option, category, latest NAV and NAV date). Combined with the data-scope statement and inactive-scheme rule, an agent has everything needed to call and interpret this tool correctly.

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% and every parameter (query, plan, option, limit, include_inactive) is documented in the schema itself, so the baseline is 3. The description reinforces the include_inactive default behavior but adds no syntax or format detail 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?

States a specific verb (search) and resource (Indian mutual fund schemes), enumerates the searchable fields (fund name, AMC, category words), and lists the returned attributes (AMFI scheme code, plan, option, category, NAV, NAV date). It also distinguishes itself from the calculator/comparison siblings by declaring it is the entry point that produces the scheme code the others consume.

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?

'Use this first to get the scheme code the other tools need' gives explicit ordering guidance relative to the sibling tools. It also states the exclusion condition for inactive schemes. It does not name which sibling to use for what, but the routing intent is clear.

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