Retainer: consulting tools

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

Annotations already declare readOnlyHint, idempotentHint and a closed-world profile, so the safety bar is low. The description adds genuinely useful behavior beyond that: the calculation is deterministic, defaults are supplied for five of six inputs, and the result is a link that opens an external calculator rather than inline numbers. The only gap is not clarifying whether the numeric values are also returned alongside the link.

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 purpose, then usage triggers, then required-input handling and return shape. The output enumeration is slightly redundant with the later link sentence, but every sentence still 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?

There is no output schema, so the description correctly carries the return-value burden by explaining that a link to the rate calculator is returned. Combined with the parameter defaults and the required-input hint, an agent has enough to call it correctly; only the ambiguity about whether raw numbers accompany the link keeps this from being fully 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?

Schema description coverage is 100%, including units, defaults, ranges and the retainer/project enum, so the schema already carries the parameter burden. The description only adds the practical cue to ask for the missing income goal and that everything else has sensible defaults; it 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 and resource ('work out what an independent consultant should charge') and enumerates the concrete outputs (minimum/recommended hourly rate, day rate, monthly equivalent, retainer). Nothing among the siblings (check_capacity, map_stakeholders, rank_client_profitability) overlaps with rate calculation, so it is immediately distinguishable.

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 when-to-use triggers: 'when someone asks what to charge, how to price a retainer, or whether their rate is too low.' It also tells the agent to ask for the income goal if unknown while noting the other inputs have defaults. No explicit when-not or named alternative, but the sibling set is disjoint, so guidance is effectively unambiguous.

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 meaningful context beyond that: the result is a link that opens an external capacity calculator, which tells the agent this is a non-mutating, referral-style operation. It does not discuss limits or edge cases, but the bar is lower with annotations present.

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: purpose and outputs first, usage trigger second, return value last. No filler, no restatement of the tool name, and every sentence contributes distinct 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 no output schema, the description usefully explains that the return value is a link to an external calculator, which is essential for an agent to interpret the result. Parameter coverage is complete via the schema and the safety profile is covered by annotations. Only minor gaps remain, such as what the link target contains or any errors on invalid hour combinations.

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 each parameter has bounds, defaults, and a description, so the schema carries the semantic load. The description echoes the concepts (billable hours, utilization, targets) but adds no format or edge-case detail (e.g. what happens if committed hours exceed total hours). Baseline 3 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?

States a specific verb and resource ('Check whether an independent consultant has room for another client') and enumerates the concrete outputs (available billable hours, current utilization, target status). It is clearly distinguishable from siblings like calculate_consulting_rate and rank_client_profitability, which address different questions.

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 concrete trigger condition: 'Use when someone asks if they can take on new work or feels stretched.' This tells the agent when to reach for this tool. It stops short of naming alternatives or exclusions (e.g. when to prefer calculate_consulting_rate instead), so it is clear but not exhaustive.

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 readOnly/idempotent/local, but the description adds real behavioral detail beyond them: the four silence thresholds, a suggested next step per contact, an overall network health score, and — with no output schema — the fact that it returns a link opening an external BD neglect detector. That is meaningful disclosure the annotations do not cover.

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 front-loaded sentences: what it checks, how it classifies, and when to use it. Every sentence carries information, with the only minor redundancy being the closing return-value note that could be tighter.

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 responsibly covers what comes back (banded contacts, next steps, health score, link) and the schema documents the single input's nested fields. An agent has enough to invoke it correctly, though the threshold boundaries' time base (per-contact last_contact vs. now) 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?

The schema itself documents the nested contact fields (name with optional company, last_contact as YYYY-MM-DD), so the structured data carries most of the load. The description adds the semantic framing that contacts include clients, past clients, and referral sources, but does not elaborate on the shape or limits (maxItems 50) 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 — checking which clients/past clients/referral sources have gone too long without contact — and specifies the exact output mechanism (day-of-silence sorting into healthy/cooling/neglected/urgent bands). An agent knows precisely what this tool computes, and it is clearly distinct from the unrelated siblings (rate calc, capacity, stakeholders, profitability).

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 conditions are given: 'Use when someone asks who to follow up with or worries their pipeline is drying up.' This is strong context, though it names no alternatives or exclusions (e.g., whether it should be preferred over rank_client_profitability for prioritization).

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 safety is covered. The description adds real value beyond that: it discloses that the tool does not store data but returns a link that opens the map in Retainer's external tool, and it explains the relative nature of scoring. It omits limits like the 30-stakeholder cap and whether the link expires.

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: purpose and quadrant taxonomy first, output artifact second, scoring caveat last. Every sentence carries information an agent needs and nothing is repeated from the schema.

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 properly explains what is returned (a link to the rendered map). Combined with annotations it covers safety, purpose and return shape. Missing are the cardinality limit (30 items) and any note on what happens if stakeholders are omitted, which is only in the schema's required field.

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 only 50%, so the description must compensate, and it does by clarifying that scores are relative ('what matters is where people sit compared to each other'), which reframes how an agent should populate power/interest. It does not explain the optional title or note fields, leaving part of the gap unfilled.

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 (sort) and resource (stakeholders on a power/interest grid), names the framework (Mendelow's matrix), enumerates the four resulting quadrants, and discloses the return artifact (a link). An agent can distinguish this from rank_client_profitability or find_neglected_relationships 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?

Usage is implied by the function ('sort stakeholders... into quadrants'), but the description never says when to pick this tool over the sibling ranking/relationship tools, nor any prerequisites such as needing names and both scores per person. Adequate context, no explicit exclusions or alternatives.

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 read-only, idempotent, closed-world behavior, so the bar is lower. The description adds genuinely useful behavioral detail beyond them: the computation performed (revenue per hour with total/average and a below-average flag) and the concrete output artifact (a link to an external calculator). It omits limits such as the 30-client maximum, but the external-link behavior is disclosed.

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 action, then usage intents, then the return artifact. Each sentence earns its place, though the usage sentence is slightly long relative to the rest.

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's explanation that it returns a link to an external calculator is important and present. It does not mention the 30-item input cap, a minor omission given how thoroughly the computation and return value are described.

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 reported as 0% at the top level, and the description supplies no information about the clients payload. However, the nested schema does describe client, monthly_fee, and hours_per_month individually, so the schema itself carries most of the semantic load and a 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?

The description states a specific verb and resource ('Rank a consultant's clients by revenue per hour') and enumerates exactly what the output contains: totals, average, and a below-average flag. This is clearly distinguishable from sibling tools like calculate_consulting_rate or check_capacity.

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 concrete triggering intents ('which clients are worth keeping, which to raise prices on, or why they're busy but not earning more'), which is strong context. It does not, however, name or exclude any sibling tool (e.g. calculate_consulting_rate) even though their subject matter overlaps.

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