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

No annotations exist, so the description carries the full burden. It usefully discloses return contents (verbatim text, page numbers, sha256, source URL) and that the server never paraphrases or extracts structured claims, which is real behavioral context. It says nothing about permissions, rate limits, or what happens when content exceeds max_chars, leaving meaningful gaps.

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 retrieval scope, then the identification methods, then the return contract. Every sentence contributes, though the enumerated headings list is dense enough to slightly bloat the middle.

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?

No annotations and no output schema, so the description must do all the work for an 8-parameter tool. It covers identification, filtering, and the shape of returned prose, but omits the semantics of max_chars (truncation behavior at the 15000 default) and return_, which matter for correct invocation.

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%, so the description must compensate, and it explains 6 of 8 parameters: doc_id, scheme_id, doc_type, as_of, query, and sections (with the exact accepted heading values). return_ and max_chars are never mentioned, which is the only material omission.

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?

Starts with a specific verb+resource ('Retrieve source-document evidence') and immediately scopes it ('the relevant pages, not the whole PDF'). It contrasts itself with sibling get_fund_profile by citing that tool's documents list as the source of doc_id, so an agent can route correctly 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?

Gives two concrete identification paths (doc_id vs scheme_id + doc_type + as_of) and explains the role of query (keyword-scoped) versus sections (SEBI-standard headings with examples). It does not state when NOT to use this tool versus the sibling profile/portfolio tools, which keeps it short of 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?

With no annotations, the description carries the full burden and does so well above average: it discloses that the benchmark comparator is not yet implemented, that it defaults to Direct/Growth with a warning when that plan is absent, and that it never emits scores/ratings/recommendations. Remaining gaps are operational (rate limits, response shape), not trust-relevant.

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-loads the purpose in the first sentence, then uses terse labeled lines for metrics/comparators and one caveat sentence. Compact and every line adds something, though the parenthetical about benchmark is slightly verbose.

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-parameter tool with no output schema and no annotations, the description covers behavior and two enum-like parameters reasonably but omits period format, the meaning of nav_series, and rolling_windows units. An agent can call it, but not with full confidence on the unaddressed parameters.

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 8 parameters, so the description must compensate. It documents valid values for metrics ('trailing','rolling','risk','drawdown','stress'), comparators ('benchmark','category'), and the plan default, but leaves period, nav_series, rolling_windows, and scheme_ids semantics unexplained.

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 resource ('Complete return/risk evidence pack') and behavior ('list = comparison'), which is enough to distinguish it from get_fund_profile or get_fund_portfolio. It stops short of explicitly naming the sibling it is not, so it lands at 4 rather than 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 description implies usage through 'list = comparison' and the enumeration of metric/comparator options, and warns about the Direct/Growth default. But it never states when to reach for this tool vs get_fund_profile or get_fund_portfolio, so the routing guidance is only implied.

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?

With no annotations, the description carries the full burden and delivers real behavioral context: corporate actions are flagged rather than asserted as trades, market-cap allocation is deliberately reported as null instead of guessed, and coverage depends on which AMC adapters have run. These are exactly the caveats an agent needs to avoid misreading output. It does not cover permissions or rate limits, but the data-quality disclosures are strong.

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 purpose sentence is front-loaded and the remaining lines are a tight parameter glossary with no filler. Slightly dense, but every line 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?

For a 7-parameter, no-annotation, no-output-schema tool, the definition covers the highest-value behavior and three parameters but leaves the semantics of as_of, provenance, holdings_limit, and scheme_ids entirely unspecified, which is a meaningful gap for an agent invoking it precisely.

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%, so the description must compensate, and it partially does: it enumerates the valid 'sections' values, the 'history' values plus the persistence-table requirement, and 'compare_to' accepted forms. However, four parameters (as_of, provenance, scheme_ids, holdings_limit) get no explanation in either schema or description.

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 set (holdings, allocations, month-over-month change detection) and scope (one or more schemes), so an agent knows this is the portfolio-composition tool rather than the performance or profile tool. It stops short of explicitly contrasting itself with siblings like get_fund_performance or get_fund_profile.

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 statement of when to use this tool versus the sibling tools. The only conditional guidance ('required for the persistence table', 'null to skip change detection') is about parameter wiring, not tool selection.

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?

With no annotations, the description carries the full burden and does unusually well on failure modes: managers and TER are 'not yet available in this build and are reported as unavailable, never fabricated', and mandate is returned as verbatim SID excerpts with page numbers rather than parsed fields. It omits auth/permission needs, result size limits, and pagination behavior.

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 sentence, then sections, then behavioral caveats — a sensible ordering. The mandate sentence is long and carries an editorial aside ('confident nonsense'), but each sentence conveys real 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?

For a 4-parameter tool with no annotations and no output schema, the description covers domain semantics (mandate handling, unavailable managers/TER) but leaves the return shape, as_of format, provenance options and pagination unexplained. Adequate but with visible 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 coverage is 0%, so the description must compensate, and it does so only for one parameter: it enumerates the valid `sections` values, information the schema lacks entirely. `as_of`, `provenance` (what values besides 'compact'?) and the required `scheme_ids` receive no explanation at all.

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 (fund profile) and enumerates its scope: identity, mandate excerpts, benchmark, costs, managers, documents. The phrase 'Static/slow-moving' implicitly separates it from the dynamic siblings get_fund_performance and get_fund_portfolio, but no sibling is named explicitly.

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 rather than stated: the 'static/slow-moving' framing tells the agent this is the reference-data lookup, and the mandate note hints that document retrieval (get_document) is the right path for investment philosophy. There is no explicit when-to-use/when-not statement or named alternative.

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?

With no annotations, the description carries the full burden. It discloses the accepted input forms and that the output is a disambiguated identity, plus the underlying ambiguity risk. It does not say what happens when multiple matches remain, how the limit affects results, or any auth/rate constraints.

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 core action and output, followed by a tightly worded justification for calling it first. No filler and nothing buried.

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?

No output schema and no annotations, so the description must cover behavior on its own. It gives input formats and the nature of the result but omits return shape, pagination via `limit`, and ambiguity-handling behavior, which an agent would need to use it reliably.

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%, so the description must compensate. It usefully expands on `query` (accepts a fund name, ISIN, or AMFI scheme code), but says nothing about the `limit` parameter or the array form of `query`, leaving half the parameters undocumented.

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 (Resolve) and resource (fund name/ISIN/AMFI scheme code) and names the exact output: unambiguous scheme+plan identity. This clearly differentiates it from the sibling get_* tools, which fetch data rather than establish identity.

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?

"Always call this first" is an explicit, actionable directive with a rationale (ambiguous Indian scheme names, renames, plan variants). It does not name when-not to use it or a specific alternative, so it stops short of a full routing statement.

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