Agent Blueprint

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

The annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description usefully adds that the text is checked and returned findings only and is not stored, plus that the linked template is the required source. It stops short of describing what a finding looks like, how many are returned, or whether failures block anything.

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 front-loaded with the verb and resource, then a dense but readable list of checks, then two short scoping sentences. The middle clause is long and list-like but every item is a distinct check, so little could be cut without losing specification.

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 must carry the return-value burden; it does so partially by stating that findings are returned and nothing is stored. For a single-parameter validator with strong annotations, that is nearly enough, with only the shape of the findings left unexplained.

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% and the single parameter is already documented as the full summary in Markdown. The description adds real meaning beyond the schema by tying the input to Agent Blueprint's specific template and noting the one-page length expectation, which constrains what valid input looks like.

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 (checks) and resource (a one-page agent summary written from Agent Blueprint's template) and enumerates the exact structural checks: eight sections in order, stage line, rule endings, Open item ownership, no placeholders, one-page length. An agent can tell immediately this is a structural validator and not a content reviewer, which also separates it cleanly from the cost, rendering, and benchmark siblings.

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 clear scope boundary — 'It checks shape only, not whether the answers are right' — which tells the agent when this tool is the wrong choice for content accuracy questions. What is missing is any positive routing guidance, such as when to run this versus estimating cost or rendering the map, though the unrelated siblings make that gap minor.

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, non-destructive, closed world), yet the description still adds real behavior: your_size scales only the reading portion while fixed agent overhead is preserved, output includes a typical and a budget/worst-case figure, and price source defaults are stated. The caveat that the result is an estimate derived from small test jobs rather than a quote is exactly the kind of expectation-setting an agent needs.

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 sentence and every following sentence carries distinct information (scaling rule, return shape, price default, caveat) with no filler. It is dense but well-ordered; a slightly tighter phrasing of the scaling sentence would make it a 5.

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 must describe returns, and it does: typical vs budget figure per run and per month when runs are given. Combined with the price-default rule and the estimate-vs-quote caveat, an agent has everything needed to call it and interpret the result.

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 3; the description earns above that by explaining the effect of your_size (proportional scaling of the reading component, fixed overhead retained) and the conditional meaning of runs_per_month (monthly figures only when supplied). It adds interpretive meaning rather than restating 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 first sentence gives a specific verb ('Estimates') plus resources ('tokens and dollar cost of an AI agent task') and the method ('from the measured benchmark job closest to it'). No sibling tool (list_benchmark_jobs, render_agent_map, check_agent_one_page, check_agent_one_page) does costing, so the agent can distinguish it immediately.

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 supplies clear situational guidance: pick the closest benchmark job, pass your_size only for jobs that scale with reading, and rely on benchmark-day prices unless current prices are supplied. It never names an alternative sibling or states an explicit 'do not use this for X' exclusion, so it stops short of the 5 bar.

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=true, destructiveHint=false, openWorldHint=false, so safety is covered. The description adds genuinely useful context beyond them: the data is measured over five runs each on Claude Code and Codex, tied to a dated benchmark snapshot, and returns typical and worst-case figures.

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, front-loaded with the resource and scope, followed by the usage instruction. Dense but every clause carries information; no filler or repetition.

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 full burden of describing return values, and it does: job identity, input size, and typical/worst-case tokens and dollar cost. The fixed count of ten jobs and dated snapshot remove ambiguity about volume and freshness.

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 the single enum parameter is fully documented in the schema, so baseline is 3. The description mentions that measurements exist for both Claude Code and Codex, which loosely motivates the filter, but adds no new detail about the parameter's behavior or defaults.

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 ('Lists the ten everyday jobs in Agent Blueprint's measured agent cost benchmark'), plus the benchmark date and the exact contents of each entry. An agent can distinguish it from estimate_agent_cost and check_agent_one_page without opening the 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 explicit when-to-use guidance: find the benchmark job closest to a target task, before estimating that task's cost. This implicitly sequences it ahead of estimate_agent_cost, but no explicit exclusion or 'don't use for X' case is 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, non-destructive, and closed-world behavior, but the description adds useful context: the output is an offline HTML file to save, the inventory is not stored, and the tool performs rendering only. It does not describe size limits or validation failures, but it meaningfully extends the annotation coverage.

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 description front-loads the core transformation and stays focused on what the tool does, what it returns, and what it does not do. The filename example and field guide link are useful, though the description is slightly longer than necessary for its level of parameter detail.

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 complex renderer with seven required parameters and no output schema, the description explains the output type and stateless behavior. It does not explain the expected input structure or validation rules, leaving much of the complexity to the external field guide and schema.

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 0% across seven required nested parameters. The description conveys high-level content such as connections, reads/changes, approvals, riskiest powers, and trimmable items, but it never explains key fields like version, drawn, checks, or unseen, nor does it clarify the many enums and constraints, so an agent still cannot reliably format most of the input.

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 specific transformation ('Turns an agent's own inventory... into... a single offline HTML page') and a clear artifact, so its purpose is easy to identify. It does not distinguish itself from related siblings such as check_agent_one_page, leaving some ambiguity about which tool to choose.

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 implies usage when an agent has an inventory and wants a visual access map, and it clarifies that the tool only draws rather than collects data. However, it gives no explicit when-to-use guidance versus siblings, no prerequisites, and no exclusions.

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