Harcourt Valuations

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

Beyond annotations (readOnly, openWorld, non-destructive), it discloses that the answer is authored by an AI assistant from Harcourt's published figures, is not investment advice, that only one question is taken per call, and that there is a per-caller daily rate limit. Provenance, disclaimer, and rate limits are exactly the behavioral context annotations cannot carry.

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?

Front-loaded with the purpose and scope, then exclusions, then provenance and constraints. Mostly earned, though the NI 43-101 / S-K 1300 / JORC sentence is supporting detail that could be trimmed without losing agent-relevant 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 single required parameter, no output schema and annotations already covering safety, the description is nearly complete: it states what can be asked, what cannot, who writes the answer, and the query limit. It stops short of describing the shape of the answer (length, whether it cites the published figures), which is the remaining minor 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 coverage is 100% and the single parameter already documents the 'name the company' requirement with an example. The description reinforces 'takes one question naming the company' but adds no format, length, or phrasing guidance beyond the schema, so 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?

Specific verb (answers a plain-English question) plus precise resource (Harcourt's published research on a covered listed mining company), with the answerable topics enumerated: published NAV per share, price to NAV at the model date, valuation drivers, and coverage list. It does not name the sibling get_published_nav, so the boundary with the structured-lookup tool is left 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?

Explicit exclusions are given: it does not value a company at today's prices or at other metal prices, which tells the agent when to avoid it. However, no alternative is named for the adjacent need (retrieving the structured published NAV), so routing between this and get_published_nav is not spelled out.

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, so the description focuses on latency and cost context: the figures are valued at the metal prices of their model date, which is returned alongside them, not at today's prices. That stale-price caveat is real behavioral context an agent needs to interpret results correctly, though return shape/pagination is not covered.

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, return fields front-loaded, with the pricing caveat last. 'exact, fast and free' is slightly promotional but functions as a differentiator, so little is wasted.

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 return burden and does so by enumerating the fields (NAV/share, P/NAV, commodity, assets, model date) and explaining the list mode. Missing only finer points like result ordering or coverage-list size, which are 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 coverage is 100% and the parameter description already documents ticker/company-name forms and the omit-to-list-all behavior. The description's restatement of the no-ticker case adds no syntax or format detail beyond the schema, so 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?

Names a specific verb and resource ('Returns Harcourt Valuations' published net asset value per share') and enumerates the returned fields, plus the list-all behavior when no ticker is supplied. It doesn't name the sibling ask_mike, so the distinction from an NL query tool is only implied by 'direct read ... exact, fast and free'.

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 no-ticker case is stated ('or the whole coverage list when no ticker is given'), which is genuine usage guidance for the only parameter. However, it never explicitly says when to prefer this over ask_mike, nor any exclusions — the contrast with the sibling is left to inference.

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