Tallybook

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, covering the safety profile. The description adds useful context about the metrics returned, but does not discuss authentication, rate limits, or other operational behavior beyond what annotations provide.

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 is a single sentence that front-loads the core subject ('Spend per sub-agent type') and lists metrics efficiently. It is slightly long but every clause contributes useful 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?

The tool has an output schema and annotations, and all parameters are documented in the schema. The description summarizes return values but omits usage context and sibling differentiation, which are gaps for an agent selecting among the many reporting tools.

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 schema already fully documents all four parameters. The description adds no additional parameter meaning, which is appropriate given the schema's completeness.

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 resource (sub-agent type) and enumerates the metrics reported (runs, model, average cost, read-only share, errors, model mismatch). The purpose is clear, but it lacks an explicit verb and does not distinguish itself from sibling tools like report or prices.

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?

There is no guidance on when to use this tool versus alternatives, no mention of prerequisites, and no exclusions. The description only lists output metrics, leaving the agent to infer context.

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, and a closed-world profile, so safety is covered structurally. The description adds useful behavioral context by defining the verdict vocabulary and asserting the figures are measured rather than estimated, but it says nothing about pagination, ordering, or how the comparison is scoped.

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, no filler, and the core purpose is front-loaded before the qualifier about measured figures. 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?

With a full input schema, an output schema, and annotations, the description does not need to describe returns or safety. It covers the tool's purpose and output semantics adequately, though a note on how verdicts are computed or when the tool is the right entry point would close the remaining gap.

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 schema already documents all six parameters (since windows, source, project matching, currency, min_runs, include_undecided). The description adds no parameter-level meaning beyond that, which puts it at the baseline of 3.

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 resource (points where a sub-agent's model changed) and a concrete output (before/after runs compared with a keep/watch/revert/too early verdict), which is clearly distinct from siblings like agents, prices, or report. It stops short of explicitly contrasting itself with those siblings, so it is not a 5.

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?

There is no guidance on when to reach for this tool versus agents, report, or session, and no mention of prerequisites or conditions. The closing line about measured figures implies a data-quality context but gives no when/when-not framing.

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, and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: it discloses the shape of the returned artifact and that a patch is only present conditionally ('if there is a file to change'), which is useful behavioral nuance.

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 sentence that front-loads the resource and the addressing key, then lists the payload contents. It is dense but every clause earns its place; 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 an output schema present and 100% parameter coverage, the description need not explain return values in depth, yet it still summarizes the payload. Annotations carry the safety profile. The only gap is the absence of explicit routing guidance versus the report tool, which is minor.

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 schema already documents id, since, source, project, and currency in detail. The description only reiterates that the id is stable and comes from report, adding minimal meaning beyond the schema. Baseline 3 applies.

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 resource ('One finding in full') and the addressing key ('its stable id from report'), and enumerates what the finding contains (what happened, why it costs, what to change, what to expect, evidence table, patch). It is clearly distinguishable from siblings like report or sessions. It lacks an explicit verb, but the purpose is unambiguous.

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 through 'its stable id from report', which tells the agent the id originates from the report tool and therefore establishes a retrieval flow. However, it never states when to prefer this over the report tool or other siblings, nor any exclusions. Adequate but incomplete guidance.

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, and closed-world behavior, so the safety profile is covered. The description adds genuinely useful non-annotation context: the unit of measure (USD per million tokens), that a verification date is included, and that user config overrides are folded in.

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 sentence that front-loads the resource and then layers unit, freshness, and override information with no filler. Every clause earns its place.

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 zero-argument read tool with an output schema and full annotation coverage, the description supplies everything needed: what the data is, its units, its provenance, and its freshness. Return-value details are correctly left to the output 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No misleading or missing parameter guidance exists because no inputs are accepted.

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 resource (the token price table) and states exactly what it contains: USD per million tokens, a last-verified date, and user config overrides. It is clear what an agent gets back, though it does not explicitly distinguish itself from the loosely-related sibling 'refresh' or other catalog tools.

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?

There is no explicit when-to-use guidance, no prerequisites, and no alternatives named. The phrase 'every figure is computed from' implies the table underlies cost calculations, but the agent must infer that it should call this tool to audit or verify pricing.

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 cover the important safety flags—idempotentHint=true, destructiveHint=false, readOnlyHint=false—but the description adds the crucial operational fact that only tallybook's own database is written. It also names the four outcome categories, which is more than the annotations provide. It doesn't describe rate limits, error modes, or how long the rescan takes.

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?

One sentence, front-loaded with the imperative action, then the returned tallies and the write guarantee. No wasted words—every clause earns its place.

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 zero-parameter, side-effecting tool with an output schema, the description plus annotations supply what an agent needs to invoke it safely and know what it will write. The main gap is not explaining what 'transcript directories' are or what prompts a rescan, but that may be out of scope for a trigger tool.

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 accepts zero parameters, which sets the baseline at 4. The description correctly and consistently indicates no configuration.

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 action (rescan transcript directories) and explains what it produces (counts of scanned, recorded, unchanged, skipped files). Its namesake siblings—agents, changes, sessions—don't overlap; refresh is set apart as the operational path that bypasses the auto-rescan.

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 clearly implies 'use this when you want the rescan to happen now rather than later', but no explicit when-not or alternative tool is named. There's no sibling that acts as the manual alternative, so the omission is 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 declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so the safety and repeatability profile is covered structurally. The description adds real context — it is machine-local and its findings list is an index into `finding` — but says nothing about cost/volume, latency, or what an empty findings list means. With annotations carrying the safety burden, this is an adequate 3.

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, no filler, and the highest-value information (what is returned) is front-loaded with the sibling handoff trailing. Every clause earns its place.

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?

An output schema exists, so the description need not enumerate return values, and it correctly focuses on the shape of the answer (total, splits, findings) plus the follow-up call. It is nearly complete; only the when-to-use versus sibling analytics tools like `sessions` or `prices` is left implicit.

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 all five parameters (since, source, compare, project, currency) are already documented in the schema, including enum-like values and the compare/since=all conflict. The description only echoes the notion of a 'window,' adding no syntax or default information beyond the schema. Baseline 3 is correct when the schema does the heavy lifting.

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 concrete resource and scope: cost of coding agents on this machine over a window, with the total, split by tool and model, and a findings list. It also distinguishes itself from the sibling tool `finding` by explaining that finding holds the full advice for a given id. An agent can pick this over `sessions` or `prices` without opening schemas.

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 explicitly routes the agent to the alternative: 'Call finding with an id from the list for the full advice,' which names both the condition and the sibling to use. It does not say when not to use report (e.g., versus `sessions` for raw per-session data) or note that since=all is incompatible with compare outside the schema, but the primary handoff is clear.

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 (readOnlyHint, idempotentHint, closed-world), so the bar is lower. The description still adds genuine value by declaring the negative space — it never returns prompt text, tool output, or command lines, and states why (the database does not hold them) — which stops an agent from chasing unavailable data.

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 short sentences, front-loaded with what is returned, followed by the accepted identifier form and the disclosure of what is withheld. Every clause carries information; nothing is padded.

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 an output schema present the description needn't explain return values, and it correctly focuses on scope and on the data it cannot supply. The one remaining gap is disambiguation from the `sessions` sibling, which matters given how similar the names are.

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 schema already defines both parameters. The description's "full session id or a unique prefix" restates the `id` schema text verbatim and says nothing about the `currency` override or the ambiguity behavior of prefixes, so it adds essentially nothing beyond structured data.

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 the resource (one session) and enumerates exactly what it returns — model, effort, token counts and cost per model response. That is concrete and distinguishes it from a generic listing tool, but it never distinguishes itself from the near-identically named sibling `sessions`, leaving the singular/plural split unexplained.

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: the framing "one session" plus the id/prefix note suggests the caller already has a single session identifier. There is no explicit statement of when to use this versus `sessions`, `report`, or `agents`, and no mention of what happens when a prefix is ambiguous.

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, idempotentHint=true, and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact not in the annotations: sub-agent runs appear as their own rows. Beyond that it discloses nothing about cost computation, auth, or limits.

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 that states the resource, the row content, the sort options, and the sub-agent inclusion with 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?

With a full schema and an output schema, return values need not be explained; the description covers scope, ordering, and non-obvious row composition. The main missing context is how it relates to the 'session' and 'agents' siblings, which an agent must infer.

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 all six parameters (sort, limit, since, source, project, currency) are fully documented in the schema. The description's mentions of sorting and window mirror existing schema text without adding syntax or format meaning, so the baseline of 3 applies.

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 the resource (sessions) and what each row contains (what each cost) plus the ordering options, so the agent knows this is a cost-oriented session listing. It does not distinguish itself from the sibling 'session' (singular) or 'agents' tools, so it falls short of a 5.

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?

The scope ('in the window') and default ordering imply this is a listing tool for session costs over a time window, but there is no explicit when-to-use, no when-not-to-use, and no alternative named despite the presence of a closely related 'session' sibling.

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