AGL Agency Capacity

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

Annotations only cover the safety profile (non-read-only, non-destructive, non-idempotent, closed-world); the description goes well beyond them by disclosing anonymity (no name, email, or company stored), a concrete rate limit (max 3 per day per network), and the consent precondition. This is exactly the extra behavioral context an agent needs before committing a write.

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 the core action, followed in order by the consent gate, the anonymity guarantee, and the rate limit. No filler or redundancy.

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 an 8-required-parameter write tool with no output schema, the description covers the decision-critical facts (consent, anonymity, quota). It omits any statement about failure handling, duplicate submission behavior, or what the collected numbers feed into, which are minor but real gaps.

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 50%, and the description adds no field-level meaning for role, revenue_band, active_clients, or account_managers, whose enum/integer semantics must be inferred from the schema alone. It does reinforce the consent parameter ('only call when the user explicitly agrees'), but that duplicates the schema's own 'Must be true' note.

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 (adds one anonymous response to the Agency Capacity Benchmark) and identifies the operator (Agile Growth Labs), so the agent knows exactly what is written. It does not explicitly contrast itself with siblings like capacity_benchmarks or capacity_check, leaving that distinction to inference.

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 gating condition: 'Only call when the user explicitly agrees to share their numbers,' which is exactly the precondition an agent needs before invoking. No alternatives or when-not-to-use cases are named beyond that, and no sibling is referenced.

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, closed-world, so safety is covered. The description adds substantive value by disclosing the return contents (8 checks, service-line checks, per-risk-level review intensity) — important since there is no output schema.

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: what it returns first, when to use it second. No filler and no redundancy with the title or annotations.

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 burden of describing returns and does so adequately for a simple read-only checklist tool with one optional enum parameter. Slightly thin on how the risk-level guidance is structured, but nothing essential 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?

The single service_line parameter is fully documented in the schema (100% coverage, enum with default). The description only implies that the parameter selects service-line-specific checks, adding marginal meaning 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 and resource: returns an 8-check review list plus service-line checks and risk-level review guidance. No sibling tool (benchmarks, capacity checks, term definition, rebrief) overlaps, so the agent can place 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?

Explicit trigger: 'Use when the user asks how to QA AI output before it reaches a client.' Clear context with no ambiguity, though it names no exclusions or alternative tools for adjacent QA questions.

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, closed-world, so the safety burden is largely lifted. The description still adds meaningfully by disclosing that results are published/sourced figures with a link per benchmark, signaling static authoritative reference data rather than computed output. It does not discuss result format or size, but that gap is minor for a static lookup.

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 tightly packed sentences with no filler: the first states what is returned, the second states when to use it. Content is front-loaded and 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 one optional enum parameter, full schema coverage, and annotations covering the safety profile, the description supplies everything needed to invoke correctly. The only shortfall is that no output schema exists and the description does not describe the returned shape beyond 'source link'.

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 baseline is 3, and the description goes one step further by glossing the enum values: 'rebriefing' is clarified as time spent re-briefing AI and 'rework' as rework of AI output. That semantic expansion genuinely helps an agent choose a topic value, though 'all' and 'accounts_per_person' are left to 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?

Specific verb and resource ('Returns published benchmarks') with the exact subject matter enumerated: accounts per account manager, time re-briefing AI, rework of AI output. An agent can tell this is a read-only reference lookup, distinct from siblings like capacity_check (computing your own capacity) and add_to_benchmark (writing to the set).

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 what is normal for agencies' gives a clear triggering context. It does not, however, name alternatives or state exclusions (e.g. 'use capacity_check instead when the user wants their own numbers'), which is the only missing piece for a 5.

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, destructiveHint false, and openWorldHint false. The description adds that the tool 'Returns an estimate, not a guarantee,' which is a useful behavioral caveat, but it does not disclose other traits like precision, input sensitivity, or output format.

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 three sentences, front-loads the purpose, follows with usage guidance, and ends with a necessary caveat. Every sentence earns its place with no redundancy.

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 appropriately names the main outputs and includes an estimate caveat. Annotations cover safety, and the schema covers parameters, so the definition is nearly complete, though it could mention optional inputs or target-ratio behavior more explicitly.

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 seven parameters. The description does not add any parameter-level detail beyond what the schema provides, making the baseline of 3 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?

The description uses a specific verb ('Estimates') and names concrete outputs: accounts per account manager, yearly coordination cost, and additional capacity at a target ratio. It does not explicitly distinguish itself from the sibling tool capacity_benchmarks, 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?

It clearly states when to use the tool: when the user shares client and team numbers and asks about capacity, hiring, or account manager load. However, it offers no when-not-to-use guidance or alternative tools, such as capacity_benchmarks.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description usefully adds that the output is a fill-in template scoped to a service line and lists its sections, but says nothing about size, format, or whether the service line changes content. With annotations carrying the safety burden, this is mid-range added context.

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, with the core purpose front-loaded before the usage cue. The parenthetical section list is dense but each item earns its place by telling the agent what the artifact contains. Slightly list-heavy, but no wasted sentences.

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 does the work of describing the return value by enumerating the template's sections (goals, voice, claims rules, priorities, approvals, decisions). Combined with the service-line scoping, an agent knows what it will get. Minor gaps: nothing about length or format of the returned template.

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 one enum's values are listed in the schema, so the schema does the heavy lifting. The description only echoes the service-line scoping ('for a service line') and never mentions client_name or the string length bound. 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 ('Returns a fill-in template for a 1-file client context document') and enumerates the exact sections the template covers, which makes the artifact concrete. It does not explicitly differentiate itself from the closely related sibling rebrief_tax, which it only alludes to via 'stop needing a client re-brief', so it stops 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?

Gives a clear usage condition: 'Use when the user wants AI tools or new teammates to stop needing a client re-brief.' That is a real when-to-use signal. It names no explicit alternative (e.g., rebrief_tax or approval_checklist) or exclusion, so it lacks the routing guidance that would earn a 5.

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, destructiveHint=false and openWorldHint=false, so safety and repeatability are covered. The description adds the empty-term listing behavior, but says nothing about matching semantics (exact vs. partial, case sensitivity) or what an unknown term returns. Adequate but not rich.

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 tightly written sentences: the purpose and examples come first, the operational mode-switch second. No filler, no repetition of the title or schema text.

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 one-optional-parameter lookup tool with safety annotations and no output schema, the description covers both invocation modes and the domain. The only gap is how term matching behaves, which an agent may want to know before passing a fuzzy term.

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 single parameter is 100% covered by the schema ('The term to define. Optional.'), which would set a baseline of 3. The description goes beyond that by explaining the special empty-value behavior — list all terms — which is meaning the schema does not convey.

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?

Specific verb ('Defines') plus a clearly scoped resource (an agency AI operations term), reinforced by four concrete example terms that pin down the domain. An agent immediately knows this is a glossary lookup, but the description never names or contrasts a sibling tool, which is the only thing keeping it from 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?

'Leave term empty to list all terms' gives an explicit mode-switch instruction that tells the agent exactly when to omit the parameter. It does not, however, address when to prefer this glossary over the sibling rebrief_tax tool, despite the overlapping 're-brief tax' term.

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 this is a read-only, idempotent, non-destructive, closed-world computation, so the safety profile is covered. The description adds the conceptual model (hours + cost of re-briefing) but omits behavior around the optional hourly_cost parameter, e.g. what the estimate does when it is not supplied.

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 with no filler: the first defines the output, the second defines the trigger. The result (what is estimated) is correctly front-loaded.

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 does state that monthly hours and cost are returned, which covers the main return-value question. For a pure-calculation tool with fully documented parameters this is sufficient, though a note on the optional hourly_cost path would complete it.

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 each parameter already carries its own definition and bounds. The description adds no unit, default, or formula detail beyond what the schema provides, 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 gives a specific verb (estimates) and resource (monthly hours and cost of re-briefing clients into AI tools), so the agent knows exactly what is produced. It is clear but does not name or contrast with any sibling tool, leaving differentiation to the reader.

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 states a concrete triggering condition: when the user asks what re-briefing AI or re-pasting client context costs. That is a usable when-to-use signal, but there is no when-not-to-use guidance or reference to an alternative sibling such as capacity_check.

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