IPO Radar — Indian IPO GMP

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds meaningful behavioral context beyond that: the statistical scope (hit rate, median and mean miss), segmentation (mainboard vs SME, by period), an additional analytical dimension (whether gains held after listing), and recency coverage (latest IPOs). It does not discuss data refresh cadence, which is the main remaining gap.

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?

Content is front-loaded with the core claim (GMP vs actual listing gain, since 2023) before the enumerated breakdowns. It is a single dense sentence whose list is slightly run-on, but every clause carries informational weight rather than filler.

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 parameters and no output schema, the description must convey what comes back — and it does, enumerating the precise metrics and segmentations in the report. An agent knows the scope (Indian IPOs since 2023), the sample size, and the analytical axes before calling.

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 no parameter semantics to document; baseline is 4. The description correctly implies a single fixed analytical report with no filtering options, so an agent will not hunt for missing arguments.

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 analytical purpose: measuring how well the last pre-listing GMP predicted actual listing gains across 1,200+ Indian IPOs since 2023, including named breakdowns (hit rate, median/mean miss, mainboard vs SME). It is clearly not a quote or listing tool like its siblings, though it never names those siblings to sharpen the distinction 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 only implied — an agent can infer this is the tool for evaluating GMP reliability rather than fetching a current GMP value. There is no explicit 'use this when…' statement, no exclusion, and no pointer to get_ipo_gmp_today for live quotes or get_upcoming_ipos for forward-looking data.

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 and openWorldHint=false, so the safety and closed-dataset profile is covered. The description adds genuine context beyond that: it discloses that some fields are conditional ('listing gain once listed') and that the profile comes 'with sources,' telling the agent to expect absent values for pre-listing IPOs. It does not cover behavior on unknown or ambiguous company names, which keeps it from a 5.

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: the verb, resource, and lookup key come first, followed by the payload enumeration. The field list is long but each item is a distinct returned data type, so it earns its place; a bulleted or grouped structure would read slightly better.

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 only one parameter, no output schema, and annotations covering the safety profile, the description's field enumeration effectively substitutes for a return-value spec, which is the main thing an agent needs. The remaining gap is behavior when the name matches nothing or matches multiple IPOs, which is left unspecified.

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 schema already provides an example ('Jio Platforms'), so the parameter is fully documented structurally. The description reinforces the lookup key as a company name but adds no matching rules, aliases, or ambiguity handling beyond the schema. 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 resource and lookup key: 'Everything on one Indian IPO by company name,' then enumerates exactly which data fields are returned (GMP history, price band, subscription buckets, dates, registrar, profile). The 'everything on one IPO' framing implicitly contrasts with the narrower siblings get_ipo_gmp_today and get_upcoming_ipos, so an agent can distinguish scope without opening the schema.

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: fetch a single IPO's full dossier when you know the company name. The description never explicitly says when to prefer this over get_ipo_gmp_today, get_gmp_accuracy, or get_upcoming_ipos, nor does it state any exclusions or prerequisites. Adequate but leaves routing inference to the agent.

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 and openWorldHint=false, so safety is covered; the description adds real value with provenance (median of three public trackers) and refresh cadence (every 30 minutes on market days). It omits any statement about staleness when markets are closed or what happens with zero matches.

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 dense sentences with the core scope front-loaded before the field list and the freshness caveat. Nearly every clause carries information, though the enumeration of output fields is slightly list-heavy for a description without an output 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 usefully enumerates what comes back (GMP in rupees and %, estimated listing price, subscription, dates, board). Filters are covered by the schema, so the only real gap is behavior on empty results or closed-market days.

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 both parameters are already documented; the baseline of 3 applies. The description glancingly reinforces them by naming 'board (Mainboard/SME)' and 'listing gain' for include_listed, but adds no format or behavior 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?

Opens with a specific verb and resource ('Live grey market premium (GMP) for Indian IPOs') and narrows scope to open, upcoming, or awaiting-listing IPOs, with an explicit field inventory. It does not name any sibling, so differentiation from get_upcoming_ipos and get_ipo is left implicit.

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 by the word 'Live' and the state filter; there is no statement of when to prefer this over get_upcoming_ipos or get_ipo. The 'refreshed every 30 minutes on market days' line hints at freshness trade-offs but never routes the agent to an 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully adds the two result cohorts and the ordering (newest filing first), but says nothing about result size, whether the pipeline list can be empty, or staleness of SEBI filing 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?

A single sentence that front-loads the primary cohort and then the secondary one, with ordering given last. No filler and no repetition of the title.

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 no-parameter list tool with annotations and no output schema, the description covers what is included and how it is ordered, which is the essential information. It stops short of describing the shape of each entry or expected volume, which would fully close the 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?

The tool takes zero parameters, so there is no parameter semantics to document; baseline applies. Nothing in the description misleads about inputs.

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 resource (Indian IPOs) and precisely bounds it: announced-but-not-yet-opened issues plus mainboard DRHP filers awaiting dates. The two-part scope and the sort order make it immediately distinguishable from get_ipo and the GMP 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?

Usage is implied by the scope ('not opened yet' vs. already-open IPOs), which is enough for an agent to route correctly in most cases. However, no sibling is named and there is no explicit when-not-to-use statement pointing to get_ipo or get_ipo_gmp_today.

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