I Bond Rate MCP

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

The annotations already state readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds real behavioral detail the annotations don't: the exact combination formula, the 0.01 percent rounding rule, and the zero floor (which implies negative inflation inputs are handled). It doesn't state the output unit or magnitude range explicitly beyond the rounding clause.

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 tight sentences with the formula front-loaded and the rounding/floor constraints attached to it. The trailing "Use it for rate predictions" is the weakest clause but costs little.

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 and does so by specifying the rounding precision and zero floor. Both required parameters are covered and the tool is a transparent pure function, so an agent has enough to call it correctly; only the explicit output unit (percent vs. decimal) is left to inference.

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 would be 3, but the description goes beyond the schema by showing how the two inputs interact (fixed + 2×inflation + fixed×inflation), which is the cross-term semantics the per-parameter schema text omits. It also signals that the inflation input can be negative via the floor, matching the schema's -10 minimum.

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 names a specific computation (Treasury composite rate formula) and spells out the exact formula, which clearly separates it from the sibling getters (get_current_i_bond_rate, get_i_bond_rate_history) and the estimator. It stops short of explicitly naming which sibling to use instead, so it is clear but not fully differentiated.

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 it for rate predictions" gives only a loose context cue and does not say when to prefer this over get_current_i_bond_rate or estimate_i_bond_value, nor any prerequisites. Usage is implied rather than specified.

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 establish that this is a safe, read-only, idempotent operation, and the description still adds real substance: semiannual compounding per $25, TreasuryDirect as the rate source, and the 3-month interest penalty applied to bonds held under 5 years. It also sets expectations that results are an estimate that can differ from Treasury values by cents, which an annotation could never convey.

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 sentences, both front-loaded with the core action and the two return values, followed by the methodology and the accuracy caveat. No filler and no repetition of schema or annotation content.

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 and does so by naming both outputs: total accrued value and redemption value after the penalty. Combined with the compounding method and the precision caveat, nothing material is missing for a three-parameter read-only estimator.

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 would be 3, but the description adds evaluative meaning beyond the schema: valuation is anchored to "the start of a month" and the output depends on holding period relative to 5 years. That clarifies how issue_month and as_of_month interact in a way the field descriptions do not.

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 uses a specific verb ("Estimate") on a specific resource ("what I bonds are worth") and names the two inputs that drive it, an issue month and a purchase amount. That clearly separates it from the sibling tools, which all deal in rates rather than dollar values.

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 scopes the calculation ("at the start of a month", "bonds under 5 years") but never says when to pick this over calculate_i_bond_composite_rate or the rate-lookup siblings, and gives no prerequisites. Usage is implied by the tool's phrasing rather than stated.

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 read-only, idempotent, and open-world behavior, and the description goes further by disclosing the data source (TreasuryDirect 'I bonds interest rates' page, read at call time) and the built-in chart fallback. It also lists what else is returned: next announcement date, $10,000 limit, 12-month hold, and 3-month penalty. The hardcoded 'November 2026 to April 2027: 5.51 percent' value is a cache-staleness risk that is not acknowledged.

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 sentences, front-loaded with the core resource and source before the supporting detail. The embedded example rate is arguably redundant with the returned payload, but it does anchor the scale of the response.

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 zero parameters and no output schema, the description carries the full burden of explaining return values, and it does so: composite, fixed, and inflation rates, next announcement date, and purchase rules. It also names the live source and fallback path, which is everything an agent needs to call this 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?

The tool takes no parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; no parameter guidance is needed.

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: read the current Series I savings bond composite, fixed, and semiannual inflation rates for new purchases. The word 'current' plus 'for new purchases' implicitly separates it from the sibling tools that handle issue-date rates, history, or composite-rate calculation.

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 by the name and by 'for new purchases', and the fallback behavior is described, but the description never explicitly says when to use this instead of get_i_bond_rate_for_issue_date or get_i_bond_rate_history, nor does it name any exclusions. An agent must infer the 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 declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new context the annotations cannot convey: the values are computed from the TreasuryDirect rate chart effective November 1, 2026, and the response spans the full lifetime of the bond including redemption status and penalty.

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 that front-loads the subject ('For an I bond bought in a given month') and then lists returns in a logical order. Every clause carries information; the only cost is that the list-form sentence is somewhat long without sub-structure.

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 carries the burden of describing return values, and it does so comprehensively — every major field of the result is named. With only two parameters, both fully described in the schema, and a stated data source, an agent has everything needed to call this 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%, so both issue_month and as_of_month are already documented with format examples. The description reinforces the issue-month semantics ('bought in a given month') and hints that as_of_month selects the evaluation period via 'current (or given) 6-month period', but adds no syntax or edge-case 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?

The description names a specific verb-and-resource pair ('For an I bond bought in a given month') and enumerates the exact outputs: fixed rate, composite rate, rate-change months, redemption eligibility and penalty, and full rate history. That is far more specific than the sibling names alone would allow, though it never explicitly contrasts itself with get_current_i_bond_rate or get_i_bond_rate_history.

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 only implied by the phrase 'bought in a given month' and by the as_of_month's 'current (or given)' wording. There is no explicit statement of when to prefer this over get_current_i_bond_rate, get_i_bond_rate_history, or calculate_i_bond_composite_rate, and no exclusions or prerequisites are given.

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?

The description goes far beyond the safety hints in the annotations by specifying the data source (TreasuryDirect), the specific announcement cadence (May and November), and the type of rates returned. This provides essential operational context for the tool's 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 definition is highly condensed into a single, powerful sentence. Every phrase serves a distinct purpose, from defining the data points to specifying the historical start date and source, achieving maximum information density.

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?

The tool is straightforward, and all necessary context—including data granularity, source reliability, and time window—is included. Given the lack of an output schema, the description is maximally complete.

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?

The schema coverage is 100%, but the description adds meaningful semantic context by explicitly stating the ordering convention ('newest first'), reinforcing the purpose of the 'limit' parameter. This helps solidify agent understanding of the result set structure.

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 clearly defines the resources being retrieved (Fixed rate, semiannual inflation rate, and composite rate) and the scope of the data (I bond rate history from TreasuryDirect). It clearly distinguishes this archival function from tools meant for current or calculated rates.

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?

While it does not explicitly state 'use this instead of X', the detailed description of historical data, announcements since 1998, and the specific content retrieved naturally guides an agent away from siblings focused on real-time or calculated values.

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